estimate
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it integrates untrusted data from task descriptions and local documents into its decision-making process.
- Ingestion points: Processes the
task-descriptionargument and reads content fromCLAUDE.md,design/gdd/,production/sprints/, and various source files. - Boundary markers: The instructions do not define delimiters to isolate external content from the agent's internal logic.
- Capability inventory: The skill is restricted to the
Read,Glob, andGreptools, which prevents it from performing high-impact actions like network access or script execution. - Sanitization: No explicit sanitization or filtering of the ingested content is specified.
Audit Metadata