meow-validate
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the
mfl(MeowFlow) CLI utility to manage workflow threads. It executes specific operations includingmfl agent update-self,mfl status, andmfl handoff appendto maintain synchronization and record validation outcomes. - [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface because its validation logic depends on data ingested from the external environment.
- Ingestion points: The agent processes output from the environment via
mfl status,mfl thread status, andmfl handoff get, in addition to reviewing project artifacts like scripts and logs (SKILL.md). - Boundary markers: The instructions do not define specific delimiters to separate external data from the primary system prompt.
- Capability inventory: The skill executes shell commands through the
mfltoolset (SKILL.md). - Sanitization: No explicit sanitization or validation steps are defined for the data read from external commands or project files.
Audit Metadata