otel-go-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data including pull request diffs, patches, and design proposals.
- Ingestion points: Code changes and documentation from the
opentelemetry-gorepository provided to the agent for review as described inSKILL.md. - Boundary markers: The instructions lack explicit delimiters or directives for the agent to disregard instructions or commands that might be maliciously embedded within the diffs or comments being analyzed.
- Capability inventory: The skill enables the agent to perform technical analysis and generate reports based on repository standards, as detailed in
SKILL.md,references/repo-rules.md, andreferences/spec-review.md. - Sanitization: No sanitization or filtering instructions are provided for handling external content before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill provides references to several authoritative external resources required for its operation.
- Fetches repository policies (CONTRIBUTING.md, CHANGELOG.md, VERSIONING.md) from the official
open-telemetry/opentelemetry-gorepository on GitHub. - References official OpenTelemetry specification documentation hosted at
opentelemetry.iofor normative behavior guidance.
Audit Metadata