013-agile-feature
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the execution of the
dateterminal command to fetch the current system date for inclusion in generated feature files. - [PROMPT_INJECTION]: The skill processes untrusted input from external epic files or pasted content which could contain malicious instructions, creating a surface for indirect prompt injection.
- Ingestion points: Epic file path or pasted content in references/013-agile-feature.md.
- Boundary markers: No explicit delimiters are present to separate untrusted content from the agent's core instructions.
- Capability inventory: Access to terminal commands (date) and file system read/write operations.
- Sanitization: No evidence of content sanitization or verification of ingested data.
Audit Metadata