Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 88% confidence
- Finding
- The skill requires an environment secret (`FAL_KEY`) and performs network-backed model invocations through `fal.ai`, but it does not declare corresponding permissions. This creates a transparency and policy-enforcement gap: an agent may execute a skill with external network access and secret usage that the permission model does not explicitly surface or constrain.
