triage-asc-issue

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches live issue data from GitHub and references documentation from an external site, sosumi.ai.
  • [COMMAND_EXECUTION]: The skill instructs the agent to run the App Store Connect CLI for reproduction and to check --help output.
  • [PROMPT_INJECTION]: The skill processes untrusted data from GitHub issues and comments, which presents a risk of indirect prompt injection.
  • Ingestion points: Reads issue body, comments, and linked PRs (File: SKILL.md).
  • Boundary markers: None identified; the agent is not explicitly told to ignore instructions found within the fetched data.
  • Capability inventory: Can execute CLI commands and interact with the local file system (docs, source, tests).
  • Sanitization: The skill lacks explicit sanitization or validation of the content retrieved from external issues.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 02:42 AM
Security Audit — agent-trust-hub — triage-asc-issue