task-verification-workflow
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses authoritative directives like 'CRITICAL' and 'MANDATORY' to enforce specific agent workflows, overriding default task completion behavior to ensure deliverable quality.
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it requires the agent to ingest and verify untrusted repository data.
- Ingestion points: repository source files and progress logs (progress.txt).
- Boundary markers: Lacks delimiters or instructions to ignore potential commands embedded within the files being analyzed.
- Capability inventory: Utilizes browser automation tools (agent-browser) and shell commands (npm, npx, grep) to interact with the environment.
- Sanitization: Does not perform validation or escaping of file content before it is processed by the agent.
- [COMMAND_EXECUTION]: The workflow specifies the execution of local shell commands, including 'npm run dev', 'npx tsc', and 'grep', which are standard for code verification tasks.
Audit Metadata