setup-matt-pocock-skills
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
git remote -vand inspects.git/configto determine the repository's hosting provider (GitHub or GitLab) to provide appropriate configuration templates. - [EXTERNAL_DOWNLOADS]: The documentation provides instructions to install the skill by cloning from the author's GitHub repository (
github.com/valorisa/Claude-Skills), which is a standard vendor resource. - [PROMPT_INJECTION]: The skill ingests data from external repository files, creating a surface for indirect prompt injection.
- Ingestion points: Reads
git remote -voutput and existing documentation files such asCLAUDE.md,AGENTS.md, andCONTEXT.md(as seen in SKILL.md). - Boundary markers: No explicit delimiters or instructions are used to separate ingested content from the agent's instructions during the summarization phase.
- Capability inventory: The skill is capable of writing configuration files to the repository root and creating new markdown files in
docs/agents/. - Sanitization: The skill does not perform validation or sanitization on the content read from the repository files before processing it.
Audit Metadata