html-debrief
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script (
scripts/prepare.sh) to validate directory structures and slugs. This is a standard initialization step for the skill's functionality. - [DATA_EXPOSURE]: The skill creates and writes to a specific local directory (
./.ai/debriefs/) within the current workspace. It implements collision checks to prevent accidental overwriting of files. - [EXTERNAL_DOWNLOADS]: The skill refers to a legitimate external resource (a GitHub repository by the same author,
paulrberg) in an error message for installation instructions if a dependency is missing. This is informative and does not perform automatic downloads. - [PROMPT_INJECTION]: No prompt injection or bypass patterns were detected. The instructions focus on grounding report content in task evidence.
Audit Metadata