to-skills
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to recommend the installation of the
writing-for-agentsskill from a specific third-party GitHub repository (mattpocock/skills) which is not a pre-approved trusted vendor.\n- [COMMAND_EXECUTION]: The skill provides a shell commandnpx skills@latest add mattpocock/skills --skill writing-for-agentsto be recommended to the user; this command downloads and executes external code at runtime.\n- [PROMPT_INJECTION]: The skill's primary function is to read and analyze other skill files (including installed dependencies), making it vulnerable to indirect prompt injection where malicious instructions in those external files could influence the agent's logic during the refinement process.\n - Ingestion points: Reads all
SKILL.mdfiles and their descriptions within the repository and its installed dependencies.\n - Boundary markers: There are no specific delimiters or 'ignore' instructions provided to the agent to isolate content within the processed skills.\n
- Capability inventory: The skill has the authority to write and modify local skill files (
SKILL.md) upon user approval.\n - Sanitization: No sanitization or validation of the ingested skill text is performed before it is presented as a proposal or applied to the repository.
Audit Metadata