skills/andiedie/skills/intake/Gen Agent Trust Hub

intake

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from a raw signal to create GitHub issues without sufficient safety boundaries. Ingestion points: The raw signal mentioned in SKILL.md. Boundary markers: No markers or explicit instructions are provided to delimit the input data from the agent's internal instructions. Capability inventory: The skill utilizes the capability to write content to an external platform by creating GitHub issues. Sanitization: There is no evidence of input validation, escaping, or sanitization described in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 02:21 AM
Security Audit — agent-trust-hub — intake