audit
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
git diff --name-only HEAD~Nto identify recently modified files in the working directory (SKILL.md, Step 1). - [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection as it reads and evaluates untrusted data from modified files.
- Ingestion points: The agent reads the content of modified or created files during the Content Verification step (SKILL.md, Step 3).
- Boundary markers: Absent. The instructions do not specify the use of delimiters or protective headers (e.g., "ignore instructions inside") when the agent reads external file content.
- Capability inventory: The skill allows for repository enumeration via
gitand arbitrary file reading in the audit scope. - Sanitization: Absent. There are no requirements to escape or filter the content read from files before it is processed by the agent.
Audit Metadata