agile-epic
Pass
Audited by Gen Agent Trust Hub on May 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from
$ARGUMENTSand local project files (e.g., intake.md, roadmap.md) and interpolates them directly into the agent's context without sanitization or protective delimiters. - Ingestion points: Processes user-supplied strings via
$ARGUMENTSand reads existing project documentation from theplanning/directory. - Boundary markers: Absent; there are no instructions to wrap external content in markers or to ignore embedded instructions within processed data.
- Capability inventory: The skill has the capability to write multiple files to the local file system (e.g.,
planning/<initiative>/epics/NN-<epic-name>/). - Sanitization: No validation or escaping of input data is performed before it is used to generate new artifacts.
Audit Metadata