spec-driven-spec-edit
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Node.js script located at
{{SKILL_DIR}}/scripts/spec-driven.jsto verify mappings. This command is triggered as part of the validation step.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes content from external project files. - Ingestion points: Accesses
.spec-driven/config.yaml,.spec-driven/specs/INDEX.md, and various spec files in the project root. - Boundary markers: Absent. There are no instructions to the agent to ignore potential commands within the files it reads.
- Capability inventory: The skill can modify filesystem content within the
.spec-driven/directory and execute shell commands (node). - Sanitization: None. The content of the read files is used directly to inform the agent's next actions.
- Mitigation: Risk is reduced by a mandatory human-in-the-loop confirmation step before any file modifications are finalized.
Audit Metadata