user-story
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection because it instructs the agent to read and process arbitrary content from the repository (README, documentation, and source code) to generate stories. This content could contain instructions meant to hijack the agent's behavior.
- Ingestion points: SKILL.md instructions tell the agent to read
AGENTS.md, the projectREADME, thedocs/folder, and source files. - Boundary markers: Absent. The instructions do not provide delimiters or warnings for the agent to ignore instructions embedded within the ingested data.
- Capability inventory: format/user-story-as-md.md directs the agent to create directories and write new files to the file system.
- Sanitization: Absent. There is no mention of filtering or validating the content extracted from the repository files.
- [COMMAND_EXECUTION]: The skill's output format instructions in
format/user-story-as-md.mddirect the agent to perform file system operations, including creating thedocs/issues/directory if it does not exist and writing markdown files to that location.
Audit Metadata