brief-company-overview

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core functionality of processing untrusted web data.
  • Ingestion points: The skill retrieves data from arbitrary external sources via WebSearch and WebFetch, including company blogs, news articles, and primary websites.
  • Boundary markers: There are no identified boundary markers or explicit instructions to the agent to disregard instructions contained within the fetched content.
  • Capability inventory: The skill possesses file system access (Read, Write) and the ability to execute directory-related shell commands (Bash).
  • Sanitization: The procedure does not describe any sanitization or validation of the fetched content before it is written to the research brief or appended to the CRM file.
  • [EXTERNAL_DOWNLOADS]: The skill uses the WebFetch tool to download external content from various third-party domains for research purposes.
  • [COMMAND_EXECUTION]: The skill performs shell command execution via the Bash tool to create directory structures (e.g., mkdir -p) based on user-supplied or discovered company slugs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 05:16 AM
Security Audit — agent-trust-hub — brief-company-overview