n8n:spec-driven-development
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes markdown files from the
.agents/specs/directory to guide implementation and verification. This establishes an indirect prompt injection surface where instructions embedded within these specification files could potentially override or bias the agent's behavior. - Ingestion points: Markdown files located in
.agents/specs/. - Boundary markers: None specified; the agent is instructed to read the full content of these files.
- Capability inventory: The agent performs file system reads and is instructed to modify implementation files or the specs themselves.
- Sanitization: No sanitization or validation of the spec content is described before processing.
- [COMMAND_EXECUTION]: The skill uses a shell command to list the contents of the specification directory.
- Evidence: The instruction
ls .agents/specs/is used to identify available specifications.
Audit Metadata