skills/howells/arc/flow/Gen Agent Trust Hub

flow

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses bash to execute sha256sum on file paths and echo to resolve environment variables. Since these inputs are derived from flow artifacts generated by analyzing the codebase, there is a risk of command injection if the project files or generated metadata contain malicious shell metacharacters.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. Ingestion points: The agent reads and parses route files and component code from the project directory to discover flows (SKILL.md). Boundary markers: There are no explicit delimiters or safety instructions provided to the discoverer agent to ignore instructions embedded in the analyzed code. Capability inventory: The skill can execute shell commands, write files to the local directory, and perform browser automation via Chrome MCP. Sanitization: No sanitization, escaping, or validation of the codebase content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 09:28 AM