recap
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the local command
forge recap <issue>to retrieve and summarize issue data. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from an issue tracker, including descriptions and comment history, which could contain malicious instructions intended to influence the agent.
- Ingestion points: Data is ingested via the output of the
forge recapcommand inSKILL.md. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present; instructions explicitly tell the agent to "Treat the recap as the authoritative current state."
- Capability inventory: The agent has the ability to run shell commands, add comments to issues, and close issues.
- Sanitization: No evidence of sanitization, validation, or filtering of the summarized issue content is provided.
Audit Metadata