gathering-planning

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies and ingests untrusted data from codebase comments and user-provided text to automate the creation of GitHub issues.
  • Ingestion points: Codebase TODO, FIXME, and HACK comments retrieved via gf --agent todo, along with user-supplied "brain dump" sessions.
  • Boundary markers: The skill lacks explicit delimiters or instructions for the agent to ignore or sanitize instructions that might be embedded within the ingested code comments or ideas.
  • Capability inventory: The skill possesses the ability to perform batch writes to GitHub via gw gh issue batch and retrieve project metadata using gw gh project list.
  • Sanitization: No explicit sanitization, filtering, or validation of the content extracted from the codebase is defined before it is processed by the sub-skills (bee-collect and badger-triage).
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 01:31 AM