maa-cli-operate
Fail
Audited by Gen Agent Trust Hub on Nov 22, 2026
Risk Level: HIGHCOMMAND_EXECUTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documentation explicitly supports arbitrary command execution through the
action shellfeature. - Evidence:
SKILL.mdstates, "Treataction shellas arbitrary command execution on the selected controller." - [DYNAMIC_EXECUTION]: The skill facilitates the dynamic loading and execution of local Python code through the
custom loadcommand. - Evidence:
references/command-contract.mdincludes the commandmaafw-cli --json custom load ./agent/main.pyand notes that it "imports and executes Python code." - [EXTERNAL_DOWNLOADS]: The skill instructions utilize
uvxto fetch and execute specific versions of themaafw-clipackage from an external registry. - Evidence:
references/command-contract.mddefines the verified release asuvx --from maafw-cli==0.1.6 maafw-cli. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its broad capabilities and ingestion of untrusted data.
- Ingestion points: The agent processes data from
ocr,reco(recognition), andpipeline runcommands, which ingest content from external screens and resource files. - Boundary markers: No specific delimiters or boundary enforcement instructions are provided to separate instructions from data within OCR or pipeline content.
- Capability inventory: The skill possesses high-risk capabilities including
action shell(arbitrary shell commands) andcustom load(Python execution). - Sanitization: The skill relies on manual human inspection ("Inspect Python files before custom load") rather than automated sanitization or sandboxing.
Recommendations
- AI detected serious security threats
Audit Metadata