verification-before-completion

Pass

Audited by Gen Agent Trust Hub on Nov 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and analyze external data to verify task completion, creating an attack surface for instructions embedded in that data.
  • Ingestion points: The skill explicitly directs the agent to read "VCS diff" (Version Control System differences) and "代理报告" (Agent reports) in SKILL.md.
  • Boundary markers: The instructions lack specific delimiters or guardrails to prevent the agent from executing instructions potentially hidden within the analyzed diffs or reports.
  • Capability inventory: The skill logic assumes the agent can execute shell commands for testing, building, and version control management to satisfy the evidence requirement.
  • Sanitization: No protocols are defined to validate or sanitize external content before it is processed by the agent.
  • [NO_CODE]: The skill consists solely of markdown instructions and metadata, with no accompanying scripts or executable files.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 17, 2026, 03:11 PM