sentry
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes curl commands to interact with the Sentry REST API at sentry.io to manage projects, issues, and releases.
- [PROMPT_INJECTION]: Potential for indirect prompt injection as the skill processes external data from Sentry which could be attacker-controlled.
- Ingestion points: Sentry API responses containing issue titles, descriptions, and stack traces (SKILL.md).
- Boundary markers: Absent. No instructions are provided to the agent to distinguish between its own logic and data retrieved from Sentry.
- Capability inventory: The skill has capabilities to create, update, and delete projects, issues, and releases via curl commands.
- Sanitization: Absent. The skill does not perform validation or escaping of content retrieved from the API before it is processed by the agent.
Audit Metadata