skills/frizzlefur/flowkit/flow-deep/Gen Agent Trust Hub

flow-deep

Fail

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill documents and utilizes a remote code execution pattern in references/capability-registry.md for installing the prime-agent tool via curl -fsSL https://app.primeintellect.ai/prime-agent/install.sh | sh. This executes an external script directly in the shell without prior integrity verification.
  • [DATA_EXFILTRATION]: The skill accesses highly sensitive local files to harvest configuration data and session history.
  • SKILL.md (Stage 0) and references/capability-registry.md (C34) instruct the agent to inspect ~/.claude/settings.json and ~/.prime/agent/auth.json to extract API keys (specifically the zai api_key).
  • The script scripts/check_context.py programmatically locates and reads Claude Code's internal project transcripts in ~/.claude/projects/, which contain the full history of user interactions.
  • [DYNAMIC_EXECUTION]: The skill dynamically assembles and injects executable prompt instructions into sub-agents based on runtime task metadata (agent_hint.type), as defined in references/skill-routing.md. This includes instructions that dictate the sub-agent's use of specific tools and workflows.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process arbitrary external data from codebases and the web, creating an attack surface for indirect injection.
  • Ingestion points: Untrusted data enters the context via Glob, Grep, Read, WebFetch, and WebSearch tools.
  • Boundary markers: While the skill uses a "Goal Contract" to define objectives, it lacks strict technical delimiters or escaping mechanisms to prevent processed data from influencing agent behavior.
  • Capability inventory: The skill possesses broad capabilities, including file modification, command execution, and the ability to dispatch further agents.
  • Sanitization: There is no evidence of input sanitization or validation of external content before it is interpolated into sub-agent prompts.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Sep 28, 2026, 03:17 AM