skills/letta-ai/skills/sentry/Gen Agent Trust Hub

sentry

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes untrusted data from the Sentry API.\n
  • Ingestion points: The agent processes issue titles, error messages, culprit data, and tags retrieved from Sentry API endpoints in scripts/sentry_api.py.\n
  • Boundary markers: No specific delimiters or "ignore instructions" warnings are used when presenting external data to the agent.\n
  • Capability inventory: The agent can execute the bundled Python script to make network requests to the Sentry API. No file-writing or arbitrary command execution capabilities are exposed.\n
  • Sanitization: The script includes logic to redact PII (emails and IP addresses) but does not sanitize strings for potential prompt injection instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 06:38 AM