workflow-feature-spec
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The instructions include a requirement to run a local Node.js utility script (
node .claude/scripts/lib/workflow-skill-contract.cjs --write) to maintain the skill's workflow calls block. This execution is limited to local project scripts and serves a documented maintenance purpose. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection as it is designed to read and process external project data, including source code and existing specification documents.
- Ingestion points: The workflow reads project configuration files (
docs/project-config.json), registry files (.claude/workflows.json), and existing specifications or code during the triage and investigation phases. - Boundary markers: The skill does not define specific delimiters or instructions for the agent to disregard potentially malicious commands embedded within the documents it processes.
- Capability inventory: The workflow can perform file system writes (to
tmp/reports/), invoke other agent skills, and execute local command-line tools. - Sanitization: The process lacks explicit sanitization steps for data retrieved from the file system before it is incorporated into the agent's context for specification generation.
Audit Metadata