anthropic-internal-comms
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) due to its core workflow of processing untrusted external data.
- Ingestion points: Instructions in
examples/3p-updates.md,examples/company-newsletter.md, andexamples/faq-answers.mddirect the agent to gather information from Slack messages, Google Drive documents, emails, and calendar events. - Boundary markers: The skill does not provide delimiters or instructions to ignore embedded commands within the fetched data, which could allow an attacker (e.g., another employee) to influence the agent's task via a malicious Slack post or document.
- Capability inventory: The skill explicitly utilizes tools with read access to the organization's communication and document storage infrastructure.
- Sanitization: There are no guidelines for sanitizing, validating, or escaping the retrieved content before it is processed by the agent.
- [NO_CODE]: The skill contains only instructional markdown and license files, with no accompanying executable code scripts (Python, JavaScript, or Shell).
Audit Metadata