skills/abpai/skills/status-update/Gen Agent Trust Hub

status-update

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from potentially untrusted external sources, such as repository contents, Pull Requests, and CI/CD status logs, to inform the status report.
  • Ingestion points: SKILL.md (Read repository, PR, CI, or runtime state).
  • Boundary markers: The instructions do not specify the use of delimiters to isolate ingested data from the summarization logic.
  • Capability inventory: The skill explicitly enforces a read-only policy ("Treat a status request as read-only. Do not interrupt workers, edit files, restart commands, deploy, or otherwise alter the task merely to report it.") and lacks any command execution or file-writing logic.
  • Sanitization: No explicit content validation or escaping is described for the gathered data.
  • [SAFE]: The skill instructions do not contain any patterns for malicious command execution, exfiltration of credentials, or remote code loading. All operations are limited to observation and reporting.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 10:40 PM
Security Audit — agent-trust-hub — status-update