Skills
skills/nolly-studio/agent-skills/bootstrap-agents-md/Gen Agent Trust Hub

bootstrap-agents-md

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from the target repository to generate documentation and operational instructions for the agent.
  • Ingestion points: The agent is instructed to read package.json, lockfiles, CI configurations (.github/workflows/), and existing documentation files like README.md or CONTRIBUTING.md from the target repository (Phase 0).
  • Boundary markers: There are no explicit instructions to use delimiters or ignore potentially malicious instructions embedded within the files being read.
  • Capability inventory: The skill possesses file-write capabilities (creating documentation and skill files under .agents/skills/) and shell execution capabilities (creating symlinks via ln -sf and running 'read-only' commands to verify script existence).
  • Sanitization: The skill lacks sanitization or validation logic for the content it summarizes from the repository, meaning malicious instructions in a README.md could be propagated into the newly created AGENTS.md or skill definitions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 02:37 PM
Security Audit — agent-trust-hub — bootstrap-agents-md