writing-review

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted user content for review.\n
  • Ingestion points: User-provided article content is interpolated into the agent context via the {content} placeholder described in SKILL.md.\n
  • Boundary markers: The skill does not define explicit delimiters or use specific instructions to prevent the model from obeying instructions potentially hidden within the user-provided content.\n
  • Capability inventory: The skill includes a capability to invoke a subsequent skill (/spencergo:writing-polish) based on the results of the review, which could allow maliciously crafted input to influence the next step in the workflow.\n
  • Sanitization: There are no patterns for validating or sanitization of the input text before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 07:35 PM
Security Audit — agent-trust-hub — writing-review