internal-comms

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and summarize data from untrusted external sources.
  • Ingestion points: The instructions in examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md direct the agent to read and process data from Slack channels, Google Drive documents, Emails, and External Press articles.
  • Boundary markers: The prompt templates lack explicit delimiters or instructions to prevent the agent from following commands that might be embedded within the processed source material.
  • Capability inventory: The skill contains no executable code or scripts, but it directs the agent to aggregate information for company-wide distribution, creating a path for misinformation if source data is poisoned.
  • Sanitization: No sanitization, validation, or content filtering logic is implemented within the skill's instructions.
  • [NO_CODE]: The skill consists entirely of markdown instruction files and does not include any executable scripts, binaries, or logic that runs in the shell.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 05:23 PM