Skills
Navigate
skills/autisticaf/claude-code-apple-dev-plugin/generators-error-monitoring/Gen Agent Trust Hub

generators-error-monitoring

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and downloads the Sentry SDK for Apple platforms from Sentry's official GitHub repository.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as rg, cat, and grep to detect existing crash reporting implementations and package configurations within the project.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from the user's project files (Package.swift and Swift source files) to determine project context. This presents a potential surface for indirect prompt injection if those files contain malicious instructions disguised as code or comments.
  • Ingestion points: Reads Package.swift and *.swift files using cat and rg in the 'Pre-Generation Checks' section of SKILL.md.
  • Boundary markers: Not explicitly defined in the instructions for data ingestion.
  • Capability inventory: The skill can write files to the local file system (Sources/ErrorMonitoring/) and modify Package.swift.
  • Sanitization: No specific sanitization or validation of the ingested code context is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 08:37 AM
Security Audit — agent-trust-hub — generators-error-monitoring