pflow-docs
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted documentation files such as READMEs and files in the docs/ directory. It lacks boundary markers to differentiate between instructions for the agent and content being edited. Mandatory Evidence Chain: Ingestion points include README*, docs/*, AGENTS.md. Boundary markers are absent. Capabilities include shell command execution (SKILL.md Step 5). Sanitization is absent.
- [COMMAND_EXECUTION]: The agent is instructed to run commands found in documentation to verify them (SKILL.md Step 5: 'Run documented commands that are safe to run'). This allows untrusted content to influence shell execution.
Audit Metadata