sentry
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from the Sentry API (e.g., issue titles, descriptions, and stack traces) which could theoretically contain malicious instructions.\n
- Ingestion points: Data is retrieved from sentry.io API endpoints via the Bash tool using curl commands (SKILL.md scenarios 1-7).\n
- Boundary markers: No specific delimiters or warnings are mentioned to isolate external data from instructions.\n
- Capability inventory: The skill has access to Read, Bash, and Edit tools (SKILL.md frontmatter).\n
- Sanitization: API responses are processed directly via jq without explicit sanitization or content filtering.
Audit Metadata