Skip to content
Report library
Purpose / Other

Using Agent Skills Skill Security Audit

What the author says it does (original text)

Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.

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.No risks found
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.Risks found: 1
Medium risk

The meta-skill makes unavailable, unaudited skills mandatory workflows

Source references: 3
What we found

The file claims authority over discovery and invocation of all skills and tells the agent to check for an applicable skill before work, execute steps in order, and skip none. Its complete-feature example extends through migration, version control, and launch. Because the invoked skills are not supplied, a user cannot determine from this source whether they run commands, modify repositories, access networks, or deploy.

Why this matters

If the agent automatically selects and follows other installed skills, the task could expand into additional code changes, commits, migrations, or release procedures. This file does not itself perform those actions and does not show that any action occurred.

The meta-skill requires the agent to find other skills before work and treats their ordered steps and verification as mandatory. Its full-feature chain can extend through version control, migration, and deployment. It also says not every task needs every skill, so deployment is not unconditional; however, the referenced skills are absent, preventing users from checking their commands, network use, or changes. Users can request all dependency texts and a permission manifest, and prohibit network, commit, migration, or deployment actions without per-action approval.

SKILL.md:3In the instructionsOpen original file
name: using-agent-skillsdescription: Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.---
Show 2 other places
SKILL.md:133In the instructionsOpen original file
1. **Check for an applicable skill before starting work.** Skills encode processes that prevent common mistakes.2. **Skills are workflows, not suggestions.** Follow the steps in order. Don't skip verification steps.3. **Multiple skills can apply.** A feature implementation might involve `idea-refine` → `spec-driven-development` → `planning-and-task-breakdown` → `incremental-implementation` → `test-driven-development` → `code-review-and-quality` → `code-simplification` → `shipping-and-launch` in sequence.4. **When in doubt, start with a spec.** If the task is non-trivial and there's no spec, begin with `spec-driven-development`.
SKILL.md:156In the instructionsOpen original file
10. test-driven-development     → Prove each slice works11. code-review-and-quality     → Review before merge12. code-simplification         → Reduce unnecessary complexity while preserving behavior13. git-workflow-and-versioning → Clean commit history14. documentation-and-adrs      → Document decisions15. deprecation-and-migration   → Retire old systems and move users safely when needed16. shipping-and-launch         → Deploy safely```Not every task needs every skill. A bug fix might only need: `debugging-and-error-recovery` → `test-driven-development` → `code-review-and-quality`.
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

7 instruction sections

This is a meta-workflow skill: it directs the agent to select other skills by task phase before doing the task. Actual follow-on behavior depends on the selected skills, whose contents are not included in this source.

View source
SKILL.md:3In the instructionsOpen original file
name: using-agent-skillsdescription: Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.---
SKILL.md:14In the instructionsOpen original file
When a task arrives, identify the development phase and apply the corresponding skill:

The document includes rules that help limit unintended changes: touch only the requested scope and avoid incidental refactoring, deletion, or unrequested features.

View source
SKILL.md:97In the instructionsOpen original file
### 5. Maintain Scope DisciplineTouch only what you're asked to touch.Do NOT:- Remove comments you don't understand- "Clean up" code orthogonal to the task- Refactor adjacent systems as a side effect- Delete code that seems unused without explicit approval- Add features not in the spec because they "seem useful"Your job is surgical precision, not unsolicited renovation.

It requires changes to be verified through tests, builds, or runtime data and refers to an external Definition of Done file that is not included in this source, so those additional requirements cannot be checked from the supplied evidence.

View source
SKILL.md:112In the instructionsOpen original file
Every skill includes a verification step. A task is not complete until verification passes. "Seems right" is never sufficient — there must be evidence (passing tests, build output, runtime data).Per-skill verification is the local check. The project-wide bar that applies to *every* change, regardless of which skill is active, is the Definition of Done: tests pass, no regressions, behavior verified at runtime, docs updated. See `../../references/definition-of-done.md`. It complements each task's acceptance criteria rather than replacing them.
Start here · InstructionsSKILL.md
using-agent-skills
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
193
File checksum (to compare versions)
47ed420eb547ebfc1cd85d742e0891c1369d5d6d0502c48d451ca59ee60de7e6