github-glowup
Pass
Audited by Gen Agent Trust Hub on Nov 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted repository READMEs and metadata, which could contain malicious instructions for the agent.
- Ingestion points: Fetches README content and file listings from GitHub repositories via the
ghCLI tool (SKILL.md, Step 0). - Boundary markers: No specific delimiters or warnings are used to isolate ingested content from the agent's primary instructions.
- Capability inventory: The skill enables the agent to update user bios, edit repository settings, and commit/push code changes (SKILL.md, Step 4).
- Sanitization: Content from external repositories is processed without explicit sanitization or filtering.
- [EXTERNAL_DOWNLOADS]: The skill utilizes
npx figletto retrieve and execute the figlet package from the npm registry for ASCII banner generation as described inREADME-STYLES.md. - [COMMAND_EXECUTION]: The script
scripts/image-to-ascii.pyinvokes system commands usingsubprocess.run()to perform image conversion viasipsormagickutilities.
Audit Metadata