sentry-integration
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze external data from Sentry (issue details, logs, and trace data) which could contain malicious payloads or instructions.
- Ingestion points: Data is retrieved from the Sentry API via MCP tools as described in SKILL.md.
- Boundary markers: No delimiters or isolation instructions are provided for processing the external data.
- Capability inventory: The agent possesses the capability to write back to the Sentry API and update issue statuses based on its analysis.
- Sanitization: There is no mention of sanitizing the ingested Sentry data before it is used to inform agent actions.
- [COMMAND_EXECUTION]: The skill documents and provides multiple shell commands for configuration and API interaction.
- Evidence: SKILL.md includes curl commands for REST API interaction, directory and file management commands (mkdir, echo, chmod) for credential storage, and system-level installation commands (pecl install) for PHP extensions.
Audit Metadata