paywall-teardown
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script (
render_report.py) included in the package to generate a visual report of the teardown. The script utilizes the standardPillowlibrary for image manipulation and does not perform any network operations. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided screenshots, which constitutes an ingestion point for untrusted data. However, the risk is mitigated by the inclusion of a rigorous scoring rubric (
references/scoring.md) and a pattern library (references/patterns.md) that the agent must use to ground its analysis. The instructions clearly state that the agent should reason only from visible elements in the screenshot. - [EXTERNAL_DOWNLOADS]: The skill instructions suggest that the agent should install the
pillowlibrary if it is missing from the environment. This is a standard dependency for the script's image processing functionality.
Audit Metadata