lov-fix-broken-links
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides legitimate functionality for finding and fixing broken links with no evidence of malicious intent or unauthorized actions. The 'profile_store.py' script is designed with security in mind, including a filter to block the storage of credentials in user records.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it reads project files (HTML, Markdown, READMEs) which are untrusted ingestion points. Boundary markers are defined in SKILL.md, specifying that analysis must remain read-only and modifications require explicit user intent. The skill is capable of file manipulation and script execution, but instructions mitigate risks by advising against speculative fixes.
- [COMMAND_EXECUTION]: The skill documentation and scripts facilitate the use of 'python3' and 'npx' for installation and maintenance. The provided scripts use standard libraries and implement safe file handling practices, such as atomic writes and strict permission management.
Audit Metadata