look-into-it
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from external sources such as Slack threads and codebase files (including
README.md,docs/, andCONTRIBUTING). This creates an attack surface where malicious instructions hidden in the analyzed content could attempt to influence the agent's investigation or code implementation behavior. - Ingestion points: The skill ingests data from Slack threads using
slack_read_threadand performs searches/reads across the codebase in theUnderstandphase. - Boundary markers: There are no explicit markers or instructions to treat external data as untrusted content, increasing the risk of the agent following instructions embedded in the analyzed data.
- Capability inventory: The skill has capabilities to read/write files, interact with Slack, and potentially execute code during the investigation (though the latter requires explicit user approval).
- Sanitization: The instructions do not specify any sanitization or filtering of external content before it is processed by the model.
Audit Metadata