coding
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to read and analyze external source code and repository instructions, creating an ingestion point for potentially untrusted data containing malicious prompts.
- Ingestion points: The workflow mandates reading 'local rules', 'repo instructions', and 'relevant source' files before performing modifications.
- Boundary markers: There are no explicit instructions or delimiters defined to isolate the source code content from the agent's internal reasoning or to ignore embedded natural language instructions.
- Capability inventory: The agent is instructed to modify code and run 'focused tests', 'type checks', 'benchmarks', 'traces', and 'validation commands'.
- Sanitization: The skill does not define procedures for sanitizing or validating instructions found within the processed files before execution or interpretation.
Audit Metadata