userstory-documentation
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, hardcoded credentials, or unauthorized network activity were detected in the skill instructions or templates.
- [PROMPT_INJECTION]: Indirect prompt injection surface identified. Ingestion points: The skill ingests untrusted data from Product Requirement Documents (PRDs) and feature specifications in Step 1. Boundary markers: The skill does not define specific delimiters or instructional barriers to prevent the agent from obeying instructions embedded within the input data. Capability inventory: The skill has permission to use 'Write', 'Edit', and 'Glob' tools, allowing it to modify files on the local system based on its processing of the input. Sanitization: There is no evidence of input validation or escaping procedures to sanitize external content before it is processed by the model.
Audit Metadata