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

sentry

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Data Exposure & Exfiltration (SAFE): The skill correctly handles authentication by requiring a SENTRY_AUTH_TOKEN environment variable rather than hardcoding secrets. It proactively redacts PII (emails and IP addresses) from API responses using the redact_data function in scripts/sentry_api.py before displaying data to the user.
  • Indirect Prompt Injection (LOW): The skill possesses a surface for indirect prompt injection as it ingests untrusted data from Sentry issue titles and logs.
  • Ingestion points: Sentry API responses fetched via scripts/sentry_api.py (issue details, events, and stack traces).
  • Boundary markers: Absent; the agent is not explicitly instructed to ignore instructions embedded within the fetched observability data.
  • Capability inventory: The skill can perform network reads to sentry.io and execute the local bundled Python script.
  • Sanitization: While PII redaction is present, there is no sanitization or filtering of the content for prompt injection patterns.
  • Command Execution (SAFE): The skill executes a bundled script (scripts/sentry_api.py) using structured arguments. It does not use shell interpolation of untrusted input or risky subprocess calls.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:57 PM