churn-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as exit survey results and CSM notes which could contain malicious instructions designed to influence the agent's behavior or the data written to the brain.\n
- Ingestion points: SKILL.md specifies reading churn reasons data from sources like exit surveys and support data.\n
- Boundary markers: The instructions do not define clear delimiters or ignore instructions for the imported data.\n
- Capability inventory: The skill has the capability to execute shell scripts (brain_query.py, brain_write.py) and modify a local knowledge base (SKILL.md).\n
- Sanitization: There is no evidence of input validation or sanitization before the data is processed or used in script arguments.\n- [COMMAND_EXECUTION]: The skill uses shell commands to interact with a local knowledge management component.\n
- Evidence: Instructions in SKILL.md direct the agent to run python3 ../professional-brain/scripts/brain_query.py and brain_write.py.
Audit Metadata