rfc-writer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied data (technical details, problem statements, and constraints) to generate structured documents, which creates a vulnerability to indirect prompt injection.
- Ingestion points: User input provided during the documentation pipeline described in
SKILL.mdandreferences/templates.md. - Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings for user-supplied content interpolated into the final output.
- Capability inventory: The skill allows access to
Write,Edit, andBashtools (defined inSKILL.md), which could be targeted by a successful injection attack to manipulate files or the local environment. - Sanitization: Absent. No explicit validation or escaping of external content is mentioned in the pipeline or instructions.
Audit Metadata