delegate-explore

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from untrusted external sources including the public web (WebSearch/WebFetch) and third-party enterprise platforms (Notion, Confluence, Jira) via MCP tools. This data is processed by subagents, creating a surface for indirect prompt injection where malicious instructions embedded in external content could influence the subagent's behavior.
  • Ingestion points: The skill explicitly reads from WebSearch, WebFetch, and MCP-connected tools (Notion, Confluence, Jira) as described in SKILL.md.
  • Boundary markers: The skill instructions recommend using "terse" requests and claim that untrusted content is isolated within child processes, which helps mitigate risks to the main agent.
  • Capability inventory: The skill uses node to execute local logic and utilizes subagents with read capabilities on the file system and external network resources.
  • Sanitization: SKILL.md states that Web/MCP content is isolated in the child process to prevent injection attacks from affecting the parent agent.
  • [COMMAND_EXECUTION]: The skill utilizes a series of shell scripts as shims to invoke local Node.js logic.
  • Evidence: Multiple files in the scripts/ directory, such as run.sh, prepare.sh, and dispatch.sh, execute node delegate-cli.mjs to perform the skill's core functions.
  • [EXTERNAL_DOWNLOADS]: The model-token-prices.json file references documentation URLs from several well-known AI and technology service providers.
  • Evidence: The file includes reference URLs to official pricing pages for Anthropic, OpenAI, Cognition (Devin), Cursor, and OpenCode. These are well-known services and the references are documented neutrally for cost analysis purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 01:47 AM