pk-lint
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is local filesystem maintenance, specifically scanning markdown files for broken links and metadata drift.
- [COMMAND_EXECUTION]: While the skill modifies project files (such as AGENTS.md and indices), it does so using internal logic for string manipulation and file I/O rather than executing arbitrary shell commands or subprocesses.
- [DATA_EXFILTRATION]: There are no network-capable commands (e.g., curl, wget) or attempts to transmit local project data to external servers.
- [PROMPT_INJECTION]: The instructions are purely operational and do not attempt to manipulate the agent's core safety instructions or bypass restrictions.
- [EXTERNAL_DOWNLOADS]: The skill does not define any external dependencies or remote script downloads.
Audit Metadata