skills/openai/skills/sentry/Gen Agent Trust Hub

sentry

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Installation via Remote Script: The skill provides instructions for installing the Sentry CLI using a shell script fetched from cli.sentry.dev (e.g., curl ... | bash). While this is a common installation method for developers, it involves executing code from an external domain, which is a typical pattern for well-known services.
  • Indirect Prompt Injection Surface: This skill processes data from Sentry, such as issue summaries and event details, which could potentially contain untrusted content.
  • Ingestion points: Data enters the agent's context through commands like sentry issue list, sentry issue view, and sentry event view in SKILL.md.
  • Boundary markers: The skill does not explicitly use delimiters around the CLI output in its instructions, though it does specify output formatting rules.
  • Capability inventory: The agent can execute various sentry CLI commands as defined in SKILL.md.
  • Sanitization: The skill includes instructions to redact PII (emails, IPs) and avoid printing raw stack traces, which helps minimize the risks associated with processing external data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 03:52 PM
Security Audit — agent-trust-hub — sentry