agile-scan-review
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes external data including code diffs and user-provided scope definitions via $ARGUMENTS, which presents a surface for indirect prompt injection where instructions in reviewed code could influence agent behavior. * Ingestion points: The skill reads $ARGUMENTS for scope and complete code diffs for review. * Boundary markers: None present in SKILL.md to distinguish between instructions and data content. * Capability inventory: The skill uses standard file reading and reporting capabilities; no privileged operations or network access requested. * Sanitization: None; the content of diffs is processed without filtering or escaping.
Audit Metadata