research.deprecation-usage

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a local script at scripts/findDeprecations.mjs using yarn node. This script is used to generate a JSON report of all deprecated members within the monorepo.
  • [EXTERNAL_DOWNLOADS]: The skill directs the agent to interact with an internal Sourcegraph instance hosted at sourcegraph.cbhq.net. This is used to query for code usage across different customer repositories. The domain appears to be an internal corporate resource associated with the author.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes code search results from external repositories. While it does not directly execute this code, the agent ingests content from these repositories, which could theoretically contain instructions designed to influence the agent's summary or reporting behavior. Standard boundary markers for external data ingestion are not explicitly defined in the provided instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 11:18 PM
Security Audit — agent-trust-hub — research.deprecation-usage