brainstorming

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data by checking project files, documentation, and git commits. This creates an entry point for instructions embedded in project content to influence agent behavior.
  • Ingestion points: The skill (in SKILL.md) specifies reading current project state, including files, docs, and recent commits.
  • Boundary markers: No specific delimiters or "ignore instructions" directives are specified for the ingested content to prevent the agent from obeying instructions found within those files.
  • Capability inventory: The skill performs file writes (docs/plans/), git operations, and invokes other workspace skills (superpowers).
  • Sanitization: No explicit sanitization or filtering of the project content is described before the agent processes it for brainstorming.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 03:46 PM
Security Audit — agent-trust-hub — brainstorming