setup-matt-pocock-skills
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from the repository root, including configuration files like
.git/configandpackage.json, as well as documentation files likeCLAUDE.md. This data is used to summarize the repository state and influence the generation of new configuration files, creating a surface for indirect prompt injection. - Ingestion points: The skill reads repository configuration and documentation files during its exploration phase (SKILL.md).
- Boundary markers: The instructions do not define clear boundaries or provide directives to ignore embedded instructions within the files being read.
- Capability inventory: The skill has the capability to write multiple documentation files to
docs/agents/and modify existing markdown files at the repository root. - Sanitization: No sanitization or validation logic for the content extracted from repository files is specified.
Audit Metadata