design
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill employs the
!datecommand to generate timestamped directory names. This is a legitimate and benign application of dynamic context injection for document management. - [PROMPT_INJECTION]: The skill reads and processes external functional requirements files, which creates a risk of indirect prompt injection.
- Ingestion points: Functional requirements are ingested from files specified in the
$ARGUMENTSvariable. - Boundary markers: The skill lacks explicit markers or instructions to delineate and ignore instructions potentially embedded within the requirements files.
- Capability inventory: The agent possesses
WriteandEditcapabilities, allowing it to modify the filesystem based on the interpreted input. - Sanitization: Content from the functional requirements files is not sanitized or validated before processing.
Audit Metadata