skills/fallow-rs/fallow/team-assembly/Gen Agent Trust Hub

team-assembly

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for a manual or cognitive task (selecting reviewers). It does not contain executable code, remote dependencies, or suspicious commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process external data, specifically a git diff and a local documentation file (docs/development/review-routing.md). This constitutes an attack surface for indirect prompt injection if the diff contains malicious instructions.
  • Ingestion points: docs/development/review-routing.md and the current git diff.
  • Boundary markers: None present; the skill lacks specific delimiters to separate untrusted data from instructions.
  • Capability inventory: None; the skill does not invoke any tools, perform network operations, or execute shell commands.
  • Sanitization: None present.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 11:12 AM
Security Audit — agent-trust-hub — team-assembly