review-adversarial

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it is designed to ingest and analyze untrusted external documents (artifacts like PRDs, architecture designs, or migration plans).
  • Ingestion points: Step 1 explicitly instructs the agent to read external artifacts in full before proceeding (SKILL.md).
  • Boundary markers: Absent. The instructions do not provide delimiters or specific warnings to the agent to ignore instructions embedded within the reviewed artifacts.
  • Capability inventory: Step 6 involves a file-write operation to a user-defined or environment-defined path {docsPath}/analysis/adversarial-review-{slug}.md (SKILL.md).
  • Sanitization: Absent. There is no mention of validation, escaping, or filtering of the content retrieved from the external artifacts before it is processed or written to the output file.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 12:59 AM
Security Audit — agent-trust-hub — review-adversarial