skills/dotlas/skills/look-into-it/Gen Agent Trust Hub

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/, and CONTRIBUTING). 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_thread and performs searches/reads across the codebase in the Understand phase.
  • 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
Risk Level
SAFE
Analyzed
Aug 28, 2026, 10:50 AM
Security Audit — agent-trust-hub — look-into-it