use-sentry

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill accesses the local Sentry configuration file at ~/.sentryclirc (as seen in scripts/detect-creds.sh) to retrieve authentication tokens. This information is used to facilitate interaction with the official Sentry API for organization and project discovery.
  • [COMMAND_EXECUTION]: The skill executes various shell commands and utilizes local binaries such as sentry, sentry-cli, jq, curl, and dig to perform project auditing, triage issues, and diagnose network connectivity.
  • [EXTERNAL_DOWNLOADS]: The skill makes network requests to the official Sentry API at sentry.io for credential verification and telemetry data retrieval. These operations target a well-known service and are consistent with the skill's stated purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, specifically Sentry issue reports and log entries, which are then processed by the agent. This represents a potential surface where malicious instructions could be embedded in an error report to influence agent behavior.
  • Ingestion points: Data fetched via sentry issue view and sentry log list (documented in references/modes/mode-3-debug.md).
  • Boundary markers: No specific delimiters or 'ignore' instructions are used when displaying fetched external data to the agent.
  • Capability inventory: The skill possesses capabilities for command execution, local file reads, and network communication with Sentry domains.
  • Sanitization: While the skill documents redacting data sent to Sentry, there is no evidence of sanitizing untrusted content retrieved from Sentry issues before it enters the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 10:27 PM