internal-comms

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from multiple corporate platforms to generate 3P updates, newsletters, and FAQs, which presents a risk of indirect prompt injection. Ingestion points: Instructions in examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md direct the agent to fetch and summarize content from Slack messages, emails, Google Drive documents, Calendar events, and external press releases. Boundary markers: The instructions lack explicit delimiters or directives to ignore instructions that may be embedded in the ingested data. Capability inventory: No executable scripts or code-based tools are provided within the skill files. Sanitization: The instructions do not define any sanitization or validation steps for the retrieved external text.
  • [NO_CODE]: The skill consists exclusively of markdown documentation and instructional files and does not contain any executable scripts, binary files, or package manager configurations.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 06:59 AM