Back to skill
Skillv1.0.0
ClawScan security
Teamgram BFF Aggregation · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 15, 2026, 4:29 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only documentation/reference skill for the Teamgram BFF aggregation layer that requests no credentials, installs nothing, and its runtime instructions are documentation-only—its declared footprint is consistent with its stated purpose.
- Guidance
- This skill is documentation-only and appears coherent with its stated purpose. Before installing: (1) verify the source link in the SKILL.md (GitHub) matches a trusted upstream repository and license (SKILL.md claims Apache-2.0), (2) be aware that documentation-only skills are low risk today but could be updated later—re-review changelogs before allowing autonomous invocation if you have a high-sensitivity environment, and (3) if you need executable functionality, prefer getting code directly from the upstream project rather than relying on a documentation skill. The only minor irregularity is the registry header showing no source/homepage while SKILL.md includes a GitHub link—confirm the registry metadata if provenance matters to you.
Review Dimensions
- Purpose & Capability
- okThe skill's name and description match the SKILL.md content (a comprehensive handler/module reference). It does not request unrelated binaries, credentials, or config paths. Minor metadata inconsistency: the registry header showed 'Source: unknown / Homepage: none' while the SKILL.md metadata includes a GitHub source/homepage (https://github.com/teamgram/teamgram-server). This is likely a packaging/manifest mismatch rather than malicious.
- Instruction Scope
- okSKILL.md is documentation-only and does not instruct the agent to read system files, access environment variables, make network calls, or transmit data. The instructions are scoped to providing a reference list of RPC modules and handlers.
- Install Mechanism
- okNo install specification, no downloads, and no code files—lowest-risk model for a skill that is purely documentation.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. The documentation itself does not access or reference secrets.
- Persistence & Privilege
- okalways is false and the skill is user-invocable; disable-model-invocation is false (the platform default). There is no request for permanent elevated presence or to modify other skills or system-wide settings.