co-parenting-messages

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through the ingestion of user-provided message history. Ingestion points: The agent processes external text provided by the user via the 'What was said' input field in SKILL.md. Boundary markers: No explicit delimiters or boundary markers are used to separate user-provided content from system instructions. Capability inventory: The skill is strictly limited to text generation; it has no capabilities for subprocess calls, network operations, file writing, or credential access. Sanitization: The skill's framework explicitly directs the agent to 'Strip the bait' and remove blame or sarcasm, focusing only on logistical facts, which serves as a natural filter for potentially malicious instructions embedded in the input text.
  • [NO_CODE]: The skill contains no executable scripts, shell commands, or external dependencies, significantly reducing its attack surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 12:04 PM
Security Audit — agent-trust-hub — co-parenting-messages