dogfood
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes the content of various local files (.py, .json, .md) to perform a self-review. Malicious instructions placed within these files could potentially be followed by the agent during the analysis process.
- Ingestion points: All .py, .json, and .md files located in the plugin's root directory.
- Boundary markers: Absent; the instructions do not specify delimiters or provide warnings to the agent to disregard instructions found within the files being reviewed.
- Capability inventory: The agent uses built-in file reading and natural language analysis to interpret and report on the code and documentation.
- Sanitization: Absent; the content retrieved from the files is processed directly without filtering or escaping.
Audit Metadata