speckit-workflow

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions include commands such as specify workflow add <url> and specify workflow catalog add <url>, which enable the downloading of automation workflows and catalogs from remote servers.
  • [COMMAND_EXECUTION]: The skill leverages the specify command-line tool to execute automation workflows through commands like specify workflow run and specify workflow resume. This facilitates the execution of defined automation steps.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external automation definitions (YAML files) that could potentially contain malicious instructions if obtained from untrusted sources.
  • Ingestion points: Local YAML files or remote workflows fetched via URL and processed by specify workflow run.
  • Boundary markers: No explicit delimiters or warnings to ignore embedded instructions are provided in the skill text for handling these external files.
  • Capability inventory: The skill provides an interface to execute commands via the specify CLI tool.
  • Sanitization: The skill does not mention specific sanitization or validation steps for the content of the workflows it manages.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 11:49 PM
Security Audit — agent-trust-hub — speckit-workflow