Skills
skills/0xdarkmatter/claude-mods/claude-code-headless/Gen Agent Trust Hub

claude-code-headless

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill describes methods for processing untrusted external data which creates a surface for indirect prompt injection attacks.
  • Ingestion points: integration examples utilize gh pr diff and cat to feed external content into the agent context in references/integration-patterns.md and references/cli-options.md.
  • Boundary markers: The examples lack delimiters or instructions to ignore embedded commands within the ingested data.
  • Capability inventory: The documented usage scenarios include the use of powerful tools such as Bash, Read, and Write as seen in SKILL.md and references/cli-options.md.
  • Sanitization: No sanitization or validation logic is present in the provided shell, Node.js, or Python integration scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 11:30 AM