handing-off-work

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local git commands such as git status -sb, git rev-parse --short HEAD, and git diff --stat to accurately capture the current state of the repository. These commands are necessary for the skill's primary purpose.
  • [SAFE]: The skill includes explicit security precautions, directing the agent to identify and remove secrets, tokens, and customer data from the handoff documents to prevent accidental exposure.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests data from the repository via git commands. Ingestion points: git status, git diff, git log in SKILL.md. Boundary markers: Absent. Capability inventory: File writing and execution of project-specific test commands. Sanitization: The skill mandates a manual check to strip secrets and verification of all claims against the repository state, which serves as a mitigation against processing malicious instructions hidden in the codebase.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 06:20 AM
Security Audit — agent-trust-hub — handing-off-work