Skip to content
skillsafebeta
← Report library
Purpose / Development

Receiving Code Review Skill Security Audit

What the author says it does (original text)

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Independent security check

Security risks found

Files checked
1
Risks found
1
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 trust for the “human partner” can bypass the Skill's own technical-verification rule

Source references: 4
What we found

The Skill requires several technical checks for external reviewers but labels feedback from the “human partner” as “Trusted - implement after understanding.” Identity alone does not establish that a suggestion is safe or correct; an impersonated account, inaccurately relayed feedback, or user mistake would not be mitigated by merely understanding the request.

Why this matters

The agent could make unverified code changes that cause regressions, introduce vulnerabilities, or alter files and project behavior.

Legitimate use of this code

Read alone, “Trusted - implement after understanding” could appear to treat identity as proof of technical correctness. However, the skill’s governing principle and explicit workflow still require checking the codebase and evaluating technical soundness before implementation, while the same subsection says to ask when scope is unclear. In context, “trusted” more plausibly identifies the person authorized to make product or architecture decisions, not permission to skip verification. The cited source therefore does not support the candidate’s claim of an across-the-board verification bypass. A user could still ask the author to clarify that trust does not override security, compatibility, or regression checks.

This assessment concerns the code and conditions shown, not proof that harm has occurred.
SKILL.md:61In the instructionsOpen original file
### From your human partner- **Trusted** - implement after understanding- **Still ask** if scope unclear- **No performative agreement**- **Skip to action** or technical acknowledgment
Show 3 other places
SKILL.md:69In the instructionsOpen original file
```BEFORE implementing:  1. Check: Technically correct for THIS codebase?  2. Check: Breaks existing functionality?  3. Check: Reason for current implementation?  4. Check: Works on all platforms/versions?  5. Check: Does reviewer understand full context?
SKILL.md:12In the instructionsOpen original file
**Core principle:** Verify before implementing. Ask before assuming. Technical correctness over social comfort.
SKILL.md:19In the instructionsOpen original file
1. READ: Complete feedback without reacting2. UNDERSTAND: Restate requirement in own words (or ask)3. VERIFY: Check against codebase reality4. EVALUATE: Technically sound for THIS codebase?5. RESPOND: Technical acknowledgment or reasoned pushback6. IMPLEMENT: One item at a time, test each```
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.No risks found

Inside this skill

8 instruction sections

The Skill's main workflow is to read and understand review feedback, verify it against the current codebase, and then implement and test items individually.

View source
SKILL.md:19In the instructionsOpen original file
1. READ: Complete feedback without reacting2. UNDERSTAND: Restate requirement in own words (or ask)3. VERIFY: Check against codebase reality4. EVALUATE: Technically sound for THIS codebase?5. RESPOND: Technical acknowledgment or reasoned pushback6. IMPLEMENT: One item at a time, test each```

For external review feedback, the Skill calls for checking compatibility, existing behavior, and the reviewer's context; when verification is unavailable, it says to disclose that limitation and ask the user how to proceed.

View source
SKILL.md:69In the instructionsOpen original file
```BEFORE implementing:  1. Check: Technically correct for THIS codebase?  2. Check: Breaks existing functionality?  3. Check: Reason for current implementation?  4. Check: Works on all platforms/versions?  5. Check: Does reviewer understand full context?IF suggestion seems wrong:  Push back with technical reasoningIF can't easily verify:  Say so: "I can't verify this without [X]. Should I [investigate/ask/proceed]?"

The Skill also says that, when replying to an inline GitHub review comment, the reply should be sent through the GitHub API to that comment thread rather than posted as a top-level PR comment. This would create external account activity under the active GitHub identity.

View source
SKILL.md:203In the instructionsOpen original file
## GitHub Thread RepliesWhen replying to inline review comments on GitHub, reply in the comment thread (`gh api repos/{owner}/{repo}/pulls/{pr}/comments/{id}/replies`), not as a top-level PR comment.
Start here · InstructionsSKILL.md
receiving-code-review
Lines connect the instruction file to its sections, not an observed execution order. Select a section to read the source. 5 more sections are available in the original file.
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
206
File checksum (to compare versions)
cbf277936578eb89b261ddbe05380af02778384ac4a7619b786616213e99a331