readthedocs-build-failure-triage
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlcommands to interact with the Read the Docs API for fetching build information and raw logs. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process raw build logs fetched from an external API (Read the Docs). While these logs represent an ingestion point for untrusted data, the skill uses this data specifically for diagnostic purposes within a defined troubleshooting workflow.
- Ingestion points: Raw build logs fetched from
${RTD_HOST}/api/v2/build/{build_id}.txt(inSKILL.md). - Boundary markers: None explicitly defined in the instructions for log processing.
- Capability inventory: Network requests via
curl(inSKILL.md). - Sanitization: None specified for the log content analysis.
Audit Metadata