pic-gen
Analysis
This skill’s image-generation behavior is coherent and disclosed, but users should understand it stores and uses API keys and depends on external Python packages.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
requests>=2.28.0 pyyaml>=6.0 banana-dev>=1.0.0
The skill depends on external Python packages with lower-bound version constraints rather than exact pinned versions. These packages are relevant to the skill, but dependency provenance and version drift are worth noticing.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
用户:「sk-xxxxxxxx」 ... Bot 写入 config/models.yaml,并回复: 「✅ Key 已保存!正在生成…」
The skill explicitly asks users to provide provider API keys and saves them locally for image generation. This is expected for the stated purpose, but the keys can authorize account usage and possible provider costs.
