recall
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reconstructs context by reading potentially untrusted external data such as chat history, GitHub issues, and PR descriptions.
- Ingestion points: SKILL.md specifies reading from conversation archives, git history, PRs, and issues.
- Boundary markers: No specific boundary markers or instructions to ignore embedded commands within ingested text are defined to separate instructions from the data.
- Capability inventory: The skill utilizes
gitandgh(GitHub CLI) to verify project state based on the gathered information. - Sanitization: While the skill includes instructions to sanitize private context before public output, it does not specify sanitization or validation of the input data to prevent embedded instructions from influencing the agent's behavior during the recall process.
Audit Metadata