friction-review

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill reads external artifacts and passes their full content to five subagents for review. While this is the intended purpose, it creates a surface where instructions embedded within the artifact could potentially influence the subagents' behavior.
  • Ingestion points: Ingests data from file paths or descriptions provided in $ARGUMENTS, as well as any files referenced within those artifacts (SKILL.md).
  • Boundary markers: Uses the ARTIFACT: header to delineate content, but does not include explicit instructions for agents to disregard embedded commands.
  • Capability inventory: Orchestrator and subagents have access to Read, Agent, Grep, Glob, and Bash tools (SKILL.md).
  • Sanitization: No input sanitization or validation is performed on the ingested content before prompt interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 11:10 AM