brooker-esque-media-satire
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown files, evaluation scenarios, and internal audit documentation. It contains no executable scripts, binary files, or network-active components.
- [SAFE]: Instructions include strong negative constraints (NEVER statements) designed to prevent copyright infringement and maintain stylistic consistency. These are safe operational guidelines rather than malicious prompt injections.
- [SAFE]: The skill includes an extensive evaluation suite (evals/ directory) that tests the agent's ability to resist user requests for near-verbatim copies of existing work, effectively acting as a security and compliance safeguard.
- [SAFE]: A shell command example (
make check-draft) is explicitly labeled as illustrative only, with a disclaimer stating the skill ships with no such script.
Audit Metadata