span-convention-review
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches latest convention documentation from develop.sentry.dev and opentelemetry.io using the WebFetch tool. These are the official documentation sites for Sentry and the OpenTelemetry project, respectively (SKILL.md).
- [COMMAND_EXECUTION]: Uses the Bash tool to execute git diff commands to identify span-related changes in the SDK repository (SKILL.md).
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from repository code and external documentation to perform its analysis (SKILL.md).
- Ingestion points: Output of git diff and content retrieved via WebFetch.
- Boundary markers: No explicit delimiters or warnings are used to separate untrusted content.
- Capability inventory: Includes Bash (for git operations), Read (for file access), and WebFetch (for network requests).
- Sanitization: No explicit sanitization or filtering of ingested content is performed before processing.
- [DATA_EXFILTRATION]: The skill actively audits tracing spans for sensitive data, including unparameterized database queries, PII in AI messages, and sensitive HTTP parameters, to prevent accidental data exposure (SKILL.md).
Audit Metadata