core-commit
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
gh apiandpython3 -cto automate data retrieval and parsing. The Python script is an inline string used to process HTML data from standard input, which is a standard pattern for this workflow. - [EXTERNAL_DOWNLOADS]: Data is fetched from
core.trac.wordpress.organdgithub.com. These are official and trusted domains for the WordPress development ecosystem. - [REMOTE_CODE_EXECUTION]: Automated scanners flagged a potential remote code execution pattern; however, the skill executes a local script string via the Python
-cflag rather than executing the content of the remote URL. - [PROMPT_INJECTION]: The skill processes untrusted content from PR descriptions and Trac comments (Ingestion: SKILL.md; Capabilities: Network, Shell Exec, File Write). While it lacks explicit boundary markers, the risk of indirect prompt injection is mitigated by the specific use case and the use of regex for metadata extraction.
Audit Metadata