product-management
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the GitHub CLI (gh) to perform core functions, including listing, creating, and syncing issues. These operations execute shell commands within the user's authenticated environment.
- [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves ingesting data from untrusted sources, creating an indirect prompt injection risk. Ingestion points: The agent reads local codebase files during the '/pm:analyze' command and fetches data from external competitor websites via the 'research-agent'. Boundary markers: The instructions do not specify the use of data delimiters or 'ignore instructions' markers when processing these external inputs. Capability inventory: The agent has permissions to execute shell commands (via gh) and write to the local '.pm/' directory. Sanitization: There is no explicit mention of sanitizing or validating the content retrieved from external websites before it is presented to the LLM.
- [EXTERNAL_DOWNLOADS]: The research functionality involves fetching and processing content from arbitrary, untrusted external domains during competitor analysis.
Audit Metadata