research-add-items

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill performs expected research management tasks using authorized platform tools. No malicious patterns such as hardcoded credentials, exfiltration, or unauthorized command execution were found.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and processing untrusted data which is subsequently stored in a project file used by other agents.
  • Ingestion points: Data is read from outline.yaml (Step 1), provided via AskUserQuestion (Step 2), and retrieved from the Task tool (Step 2).
  • Boundary markers: The instructions do not define specific markers or delimiters to separate untrusted data from instructions within the YAML structure.
  • Capability inventory: The skill uses Read, Write, Glob, and Task tools.
  • Sanitization: No sanitization or content validation logic is applied to the gathered research items prior to writing them to the filesystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 04:17 PM
Security Audit — agent-trust-hub — research-add-items