sentry-cli
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides installation commands that fetch the Sentry CLI binary from the official sentry.dev domain via curl and pipe it to bash. This is standard vendor-provided installation logic for the Sentry ecosystem.\n- [COMMAND_EXECUTION]: The core purpose of the skill is to enable AI agents to execute the sentry command-line tool. This includes performing mutations such as creating or deleting projects, managing authentication, and querying Sentry API for issues and traces.\n- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests data from external sources like Sentry issue summaries and event payloads.\n
- Ingestion points: Commands such as sentry issue view and sentry event view bring untrusted external data into the agent context (SKILL.md).\n
- Boundary markers: No formal delimiters are specified in the instructions.\n
- Capability inventory: The agent can execute shell commands and network requests through the CLI.\n
- Sanitization: The documentation explicitly instructs agents to use the --fields flag to select only necessary data and avoid exposing sensitive session information like cookies found in full event objects.
Audit Metadata