Skip to content
Report library
Purpose / Other

Firebase Security Rules Auditor Skill Security Audit

What the author says it does (original text)

>-

Independent security check

Security risks found

Files checked
1
Risks found
2
Could it run dangerous commands?Looks for programs run straight after downloading, remote control of your computer, and hidden commands.No risks found
Could it expose your files or keys?Looks for uploads of files containing passwords or keys, and keys written directly in the code.No risks found
Could it delete files or keep running?Looks for broad file deletion, disk overwrites, and programs set to start automatically.No risks found
Could it bypass safety checks?Looks for skipped website security checks, excessive file access, or actions that skip your approval.Risks found: 1
Medium risk

Blanket exemption for a hardcoded admin email may hide single-account privilege risk

Source references: 1
What we found

The Skill asserts that admin bootstrapping is limited and directs the auditor not to deduct points for one hardcoded admin email if the email is verified and additional admins cannot be added. The source provides no application design or threat model supporting that premise. Email verification does not address account takeover, rotation, or single-point-of-compromise risk.

Why this matters

When rules grant admin access through one hardcoded email, the assessment may score them too highly and lead users to overlook that compromise of that account could expose all administrator powers.

The instruction explicitly tells the auditor not to reduce the score for a hardcoded administrator email when email verification is checked and additional admins cannot be added. Email verification confirms current control of the address but does not assess takeover, rotation, or recovery risks, and the source provides no application threat model showing those risks are accepted. This can produce an overly favorable security score. A user can ask that these residual risks be reported separately, including rotation, recovery, and strong-authentication requirements.

SKILL.md:49In the instructionsOpen original file
The admin bootstrapping process is limited in this app. If the rules use asingle hardcoded admin email (e.g., checking request.auth.token.email =='admin@example.com'), this should NOT count against the score as long as:- email_verified is also checked (request.auth.token.email_verified == true).- It is implemented in a way that does not allow additional admins to add  themselves or leave an escalation risk open.
Could it mislead the AI or hide text?Checks the skill instructions for requests to ignore you, influence the report, or hide text in invisible characters.No risks found
Could it change links or payment recipients without asking?Looks for forced referral or payment changes combined with instructions to hide the change.Risks found: 1
Medium risk

Resource-exhaustion risk is preset as minor, potentially understating availability and cost impact

Source references: 2
What we found

The checklist says missing string or array limits must be labeled “Resource Exhaustion/DoS,” yet the scoring criteria place lack of size limits among minor issues. This fixed downgrade does not consider write frequency, billing, or business availability and can suppress the appropriate severity.

Why this matters

If an attacker can submit repeated or oversized data, a low score may cause users to underestimate increased storage, read, and processing charges or service degradation.

The checklist requires missing string or array size limits to be labeled as resource-exhaustion/DoS risk, while the scoring rubric presets “lack of size limits” as minor. If rules permit frequent or costly writes, that classification may understate outage and billing impact; the source does not require severity adjustment for write rate, document limits, billing, or business criticality. A user can ask the author to rate this by practical exploitability, cost exposure, and availability impact instead of automatically treating it as minor.

SKILL.md:35In the instructionsOpen original file
   data? If not, the rules are "broken" or will force insecure workarounds).1. **Storage Abuse:** Are there string length or array size limits? If not,   label it as a "Resource Exhaustion/DoS" risk.1. **Type Safety:** Are fields checked with 'is string', 'is int', or 'is
Show 1 other places
SKILL.md:64In the instructionsOpen original file
  (create vs update) on critical fields- **4 (Minor):** Problems that result in self-data corruption like update  bypasses that only impact the user's own data, lack of size limits, missing  minor type checks or over-permissive read access on non-sensitive fields.- **5 (Secure):** Comprehensive validation, strict ownership, and role-based

Inside this skill

1 instruction sections

This Skill contains only audit prompts and scoring guidance; the supplied source has no scripts, installation steps, network requests, credential access, or file-modification instructions. It directs reviews of Firestore/Cloud Storage rules for update bypasses, authority sources, ownership, types, and size limits.

View source
SKILL.md:24In the instructionsOpen original file
### Mandatory Audit Checklist:1. **The Update Bypass:** Compare 'create' and 'update' rules. Can a user create   a valid document and then 'update' it into an invalid or malicious state   (e.g., changing their role, bypassing size limits, or corrupting data types)?1. **Authority Source:** Does the security rely on user-provided data
SKILL.md:39In the instructionsOpen original file
   timestamp'?1. **Field-Level vs. Identity-Level Security:** Be careful with rules that use   \`hasOnly()\` or \`diff()\`. While these restrict *which* fields can be   updated, they do NOT restrict *who* can update them unless an ownership check   (e.g., \`resource.data.uid == request.auth.uid\`) is also present. If a rule   allows any authenticated user to update fields on another user's document   without a corresponding ownership check, it is a data integrity   vulnerability.

The Skill tells the model to search actively for sequences of operations that bypass rules rather than treating complexity as proof of security. This is static review guidance, not evidence that attacks will be executed.

View source
SKILL.md:19In the instructionsOpen original file
You are a Senior Security Auditor and Penetration Tester specializing inFirestore. Your goal is to find "the hole in the wall." Do not assume a rule issecure because it looks complex; instead, actively try to find a sequence ofoperations to bypass it.
Start here · InstructionsSKILL.md
firebase-security-rules-auditor
Lines connect the instruction file to its sections, not an observed execution order. Select a section to read the source.
Files and check records1 files

Coverage and gaps

Content covered in each file

These are the source ranges included in this check, not a guarantee that every issue has been resolved.

  • SKILL.mdFull text included

This report is for the version above. We read the available code and instructions without running the skill or checking extra packages it installs. This is not a promise of safety: a different version or setup may behave differently.

  • SKILL.mdInstructions
Lines read
74
File checksum (to compare versions)
265530296ade65de2c1189d955da98f410836c889d93868b085e4b09439d368a