packaging-workshop
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script located at ~/.grok/skills/zan-punct-fix/scripts/fix_punctuation.py when punctuation checks are requested for files or directories. This command includes a --dry-run flag and is intended for automated editing tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection.
- Ingestion points: The skill ingests untrusted text for polishing and user-specified file paths for punctuation fixing (SKILL.md).
- Boundary markers: The instructions do not define clear delimiters or use explicit warnings to ignore instructions embedded within the user's content.
- Capability inventory: The skill has the ability to run a Python script on local file paths and output modification reports.
- Sanitization: There is no evidence of path validation or content sanitization before the script is executed or the text is processed.
Audit Metadata