init-agents-md

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data from repository files to generate a new markdown file.
  • Ingestion points: Processes content from README.md, pyproject.toml, package.json, and various configuration files.
  • Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between legitimate project metadata and potentially malicious instructions embedded in the source files.
  • Capability inventory: The skill utilizes file read and write capabilities within the project root.
  • Sanitization: No sanitization or validation of the ingested content is defined before it is formatted into the final AGENTS.md file.
  • [NO_CODE]: The skill consists entirely of markdown-based instructions and does not include any executable scripts or binary files, which limits the scope of potential technical attacks to prompt-based vectors.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 02:37 AM