example-skill
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
git diff --cachedto retrieve staged changes. This is a local read operation necessary for the skill's primary function and does not involve elevated privileges. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it analyzes untrusted data (code changes) without sanitization.
- Ingestion points: Staged changes from
git diff --cachedin SKILL.md. - Boundary markers: No delimiters or warnings are used to separate code from instructions.
- Capability inventory: Limited to local read-only access to git metadata; no network or file-write capabilities were found.
- Sanitization: The skill does not escape or validate the contents of the diff before processing.
Audit Metadata