agents-md-improver
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to discover, audit, and modify project rules files (such as
AGENTS.mdandCLAUDE.md) within a repository, creating a potential surface for indirect prompt injection if those files contain malicious instructions. - Ingestion points: The skill reads repository files, diffs, tests, comments, PR metadata, issue descriptions, and existing project rules files as specified in
SKILL.md. - Boundary markers: Present. The 'Untrusted data boundary' section explicitly instructs the agent to treat repository content as data rather than instructions and to ignore any embedded directives.
- Capability inventory: The skill possesses the capability to write or edit project rules files via the environment's editor tool. No dynamic execution or subprocess command tools are invoked.
- Sanitization: The skill mandates that secrets or private credentials discovered during processing must be replaced with
[REDACTED]placeholders.
Audit Metadata