rfc

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Potential indirect prompt injection surface identified through untrusted file processing.
  • Ingestion points: The skill reads from local project files such as RFCs (docs/rfcs/*.md), research artifacts, and Architecture Decision Records (ADRs) to gather context for updates and reviews (WORKFLOW.md).
  • Boundary markers: The skill does not use explicit delimiters or instructions to isolate document content from agent logic, potentially allowing embedded instructions to influence the agent.
  • Capability inventory: The skill can write to the file system and delegate tasks to a sub-agent (doc:rfc-critic) which is granted Bash access to verify claims made in documents. This combination could be exploited if malicious content is processed.
  • Sanitization: No sanitization or content validation is performed on the data extracted from the documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 10:55 AM