internal-comms

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access attempts were detected in the skill instructions or examples.
  • [NO_CODE]: The skill is composed entirely of markdown documentation and templates. It does not include any scripts, executable files, or package dependencies.
  • [PROMPT_INJECTION]: Potential for indirect prompt injection is noted as the skill instructs the agent to ingest data from external sources like Slack and Email. This is a common surface for such tasks and is handled here with standard document-gathering instructions.
  • Ingestion points: Slack messages, Google Drive documents, Emails, and External press (referenced in examples/3p-updates.md and examples/company-newsletter.md).
  • Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore instructions within the ingested text.
  • Capability inventory: No executable code or subprocess calls are present in the skill files; it relies on the agent's native toolset.
  • Sanitization: Absent; no data validation or sanitization steps are specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 04:39 PM
Security Audit — agent-trust-hub — internal-comms