skill-reviewer
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and suggests the installation of the 'writing-skills' dependency from a public GitHub repository (github.com/obra/superpowers).
- [COMMAND_EXECUTION]: The skill executes local automation scripts ('validate.sh' and 'quick_validate.py') to perform structural and formatting checks on skill files.
- [PROMPT_INJECTION]: The skill processes external, potentially untrusted content from third-party skills, creating a surface for indirect prompt injection. \n
- Ingestion points: The skill reads the contents of 'SKILL.md', 'scripts/', and 'references/' from target skills during Step 3 of the audit. \n
- Boundary markers: There are no explicit delimiters or protective instructions provided to the agent to differentiate between audit metadata and instructions contained within the files being scanned. \n
- Capability inventory: The skill possesses the capability to execute shell commands and run Python code via its included scripts. \n
- Sanitization: Content from the audited files is not sanitized or escaped before being presented to the agent for analysis.
Audit Metadata