critic-dialogue

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process arbitrary text from external documents (implementation plans, PRs, design docs), which presents a surface for indirect prompt injection attacks.
  • Ingestion points: Untrusted data enters the agent context via the {path} variable in SKILL.md, the {document path} in chunker.md, and the {list of original plan file paths} in reviser.md.
  • Boundary markers: The skill uses structured markdown headers (e.g., ### Your scope — review this) to isolate the review target, but does not provide explicit instructions for the model to ignore or treat instructions inside the ingested text as data rather than commands.
  • Capability inventory: The skill includes file-read capabilities across all stages and file-write capabilities in the reviser.md stage to apply changes to project files.
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the ingested content before it is processed by the critic or dev-response subagents.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 01:37 PM
Security Audit — agent-trust-hub — critic-dialogue