pm-report
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill preamble contains a bash script that executes an external file
../../check-update.shusing a relative path. This creates a functional dependency on the specific directory structure of the host environment.\n- [INDIRECT_PROMPT_INJECTION]:\n - Ingestion points: The skill collects report configuration, user metrics, and feedback text via the
AskUserQuestiontool in Steps 1, 2, and 4.\n - Boundary markers: Absent. There are no instructions or delimiters provided to isolate user-supplied input from the structural text of the generated reports.\n
- Capability inventory: The skill uses the
Writetool to create documentation files andBashfor directory and script operations.\n - Sanitization: Absent. The instructions do not specify any validation or escaping of user input before it is written to the
docs/directory.
Audit Metadata