git-memory
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill implements a retrieval mechanism (
scripts/memory-grep.sh) that ingests data from git commit trailers and GitHub PR bodies. This content is potentially attacker-controlled in shared repositories and is fed into the agent's context, creating an indirect prompt injection surface. - Ingestion points: The
memory-grep.shscript extracts text fromgit logoutput andgh pr listdata to compile project memory. - Boundary markers: The skill does not currently implement explicit boundary markers or 'ignore embedded instructions' warnings when presenting retrieved memory data to the AI agent.
- Capability inventory: The skill is designed to influence sensitive operations such as
git commitandgh pr create, meaning instructions retrieved from memory could potentially misguide the agent's actions during these tasks. - Sanitization: No sanitization or safety filtering is performed on the retrieved text content before it is processed by the agent.
Audit Metadata