opportunity-factory

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes utility and testing scripts that execute system commands.
  • Evidence: scripts/smoke_test_initializers.py uses subprocess.run to execute init_factory_workspace.py and init_factory_sqlite.py during validation.
  • Context: These are used for internal development, smoke testing, and workspace initialization within the skill's own environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves discovery tasks that ingest and analyze untrusted external data.
  • Ingestion points: discover and research tasks (defined in references/workflow.md) mine data from external sources such as web search results, social media, app reviews, and forums.
  • Boundary markers: While the system uses structured JSON and Markdown, it lacks explicit "ignore instructions" delimiters when the worker role processes raw external text strings.
  • Capability inventory: The agent has capabilities for file system writes (state and artifacts), subprocess execution (initialization scripts), and network operations (web fetching).
  • Sanitization: No explicit sanitization or escaping of external content is documented before it is interpolated into local artifacts or state logs.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates automated data collection from external web sources.
  • Evidence: references/fallback-lane.md and references/workflow.md describe roles for fetching web search results and API data for evidence collection.
  • Context: These are read-only operations intended for market research and are subject to the auto bucket approval policy, which forbids sending sensitive data externally.
  • [DYNAMIC_EXECUTION]: The skill includes a "Prompt Self-Improvement Loop" allowing it to modify its own internal instructions.
  • Evidence: references/prompt-self-improvement.md details how the agent can edit workspace-local prompts (.github/prompts/*.md).
  • Context: This autonomous modification is restricted to local workflow assets and requires a Layer 3 blocking critic (from a different model family) and a successful smoke test before changes are committed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 08:22 AM
Security Audit — agent-trust-hub — opportunity-factory