write-spec
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process data from untrusted or external sources, creating a surface for indirect prompt injection attacks.
- Ingestion points: The agent is directed to "read in full" any file, issue, or URL provided in arguments, as well as specific project files like
spec/vision.md,spec/glossary.md, andSKILL.mdfiles located in.agents/skills/. - Boundary markers: The instructions do not define clear delimiters or provide the agent with specific warnings to ignore or neutralize instructions embedded within the ingested data.
- Capability inventory: The skill possesses capabilities to search the codebase, read arbitrary files and URLs, and write new specification files to the project directory (
spec/features/<slug>/spec.md). - Sanitization: There are no documented steps for sanitizing, escaping, or validating the content retrieved from external URLs or project files before it is used to generate the output spec.
Audit Metadata