edge-case-finder
Pass
Audited by Gen Agent Trust Hub on May 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses standard git commands (
git status,git diff) to perform repository analysis, which is appropriate for its stated purpose as a QA assistant. - [PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection (Category 8) as it processes untrusted code content from git branches.
- Ingestion points: Reads code and comments from git diffs in
SKILL.md. - Boundary markers: Lacks explicit markers to isolate analyzed code from agent instructions.
- Capability inventory: The skill can execute shell commands via
gitand modify local files to apply fixes. - Sanitization: No validation or sanitization is performed on the ingested code changes.
Audit Metadata