pm-report
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's preamble contains shell commands that execute a local script
check-update.shand perform workspace initialization tasks such as directory creation (mkdir -p). These actions are standard for setting up a local reporting environment. - [PROMPT_INJECTION]: The skill facilitates the collection of untrusted data from users (e.g., performance metrics, feedback text) which is subsequently interpolated into generated reports. There is a risk of indirect prompt injection as the skill lacks explicit boundary markers or input validation, though this is a common characteristic of such reporting tools.
- Ingestion points: Data collection occurs via
AskUserQuestionin Steps 2 and 4. - Boundary markers: None present in the instructions.
- Capability inventory: The skill has permissions for
Writeoperations (to save reports) and theBashtool. - Sanitization: No sanitization or escaping mechanisms for user input were found.
Audit Metadata