Back to skill
Skillv1.0.0
ClawScan security
SnapOG · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 12, 2026, 3:51 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is internally consistent: it only needs a SnapOG API key and its instructions match the described image-generation purpose.
- Guidance
- This skill appears to do exactly what it says: call the SnapOG API using SNAPOG_API_KEY to generate images. Before installing: (1) keep your SNAPOG_API_KEY secret (don’t paste it into public repos or share it), (2) be cautious when using webhook_url or creating signed URLs — only point webhooks to trusted endpoints and keep signed-URL expirations short so you don't unintentionally publish private content, (3) verify you trust https://snapog.dev (check their docs/TOS/privacy) since generated assets and parameters will be sent to that service, and (4) rotate the API key if you suspect it was exposed. Overall there are no incoherent or disproportionate requirements in this skill.
Review Dimensions
- Purpose & Capability
- okName/description (generate OG/social images) matches the requirements and runtime instructions. The only required secret is SNAPOG_API_KEY which is appropriate for an API-backed image generation service.
- Instruction Scope
- noteSKILL.md instructs the agent to call the SnapOG API and to read SNAPOG_API_KEY from the environment — this is expected. The docs also mention features that can transmit results externally (webhook_url and creating signed URLs that work without auth). These are API features (not hidden agent behavior) but are worth noting because a user could accidentally expose generated images or create signed URLs with too-long expiry or point webhooks at attacker-controlled endpoints.
- Install Mechanism
- okNo install spec and no code files — instruction-only skill. Nothing is downloaded or written to disk by the skill itself.
- Credentials
- okOnly SNAPOG_API_KEY is required and declared as the primary credential. That is proportionate to the stated functionality; no unrelated secrets or config paths are requested.
- Persistence & Privilege
- okalways is false and the skill does not request persistent system presence or modify other skills. Agent autonomous invocation is allowed by default but is not combined with any elevated privileges here.