deepen-plan

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes external data with powerful tools.
  • Ingestion points: The skill ingests data from external plan documents or issues via the Read tool during Phase 1.
  • Boundary markers: The prompt lacks explicit delimiters or instructions to treat ingested content as untrusted, which may allow embedded instructions to influence agent behavior.
  • Capability inventory: The skill is configured with high-impact capabilities including Bash, Write, and Edit tools.
  • Sanitization: There is no evidence of validation or sanitization of the data read from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 03:08 PM