best-programmer
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and analyze external, potentially untrusted data including error messages, stack traces, and third-party source code. \n
- Ingestion points:
SKILL.md(Step 2 and Step 3A) directs the agent to read project source code, documentation, and error logs from the environment to perform technology research and debugging. \n - Boundary markers: There are no explicit instructions provided to the agent to use delimiters or ignore instructions that might be embedded within the source code or log files being analyzed. \n
- Capability inventory: Use cases for this skill include implementation and debugging, which typically involve the ability to execute shell commands and modify files. \n
- Sanitization: No methods for sanitizing or validating external content are identified in the skill's instructions.
Audit Metadata