pm-release
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill preamble executes a local shell script (check-update.sh) located in a relative path. This is a common maintenance pattern for managing updates within a local repository environment and does not involve remote code execution or suspicious external sources.
- [INDIRECT_PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it processes user-supplied data into final documentation.
- Ingestion points: User data is ingested through the AskUserQuestion tool in Steps 1 through 5 of the SKILL.md execution flow.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when the user's responses are interpolated into the final document template.
- Capability inventory: The skill has access to the Bash tool (initialization), Write tool (file creation), and Agent tool (subagent orchestration).
- Sanitization: There are no requirements for the agent to sanitize or validate user input before writing it to the generated markdown file in the docs directory.
Audit Metadata