agent-mdlint
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external instruction files (e.g.,
AGENTS.md) and diffs which could contain malicious instructions. - Ingestion points: The skill instructs the agent to "read the complete before and after versions" and compare diffs of instruction files in
SKILL.md. - Boundary markers: There are no specific delimiters or boundary markers defined to isolate the untrusted content being reviewed from the agent's instructions.
- Capability inventory: The skill does not specify the use of network tools, file system writes (other than authorized edits to the source), or subprocess execution.
- Sanitization: No sanitization or escaping mechanisms are defined for processing the external text.
- [NO_CODE]: The skill consists entirely of Markdown instructions and YAML configuration metadata. It does not include any scripts, executables, or third-party dependencies.
Audit Metadata