ClawHub
Back to skill

Security audit

AgentYield.co

Security checks for vulnerabilities and agentic risk

Overview

AgentYield is a disclosed observability skill that sends bounded, redacted LLM/tool-call telemetry to its own API for cost and waste analysis.

Before installing, be comfortable with session-wide telemetry leaving your environment: model names, token counts, costs, tool names, timestamps, purpose tags, and salted hashes of tool inputs are sent to AgentYield. Use a test-mode API key for evaluation, and revoke the key if you stop using the service.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 332)May include surrounding context.

md
- This `SKILL.md` is the source of truth and is served at <https://agentyield.co/skills/agentyield.md> for inspection before install.

Unbounded Output

Medium
Category
Output Handling
Confidence
60% confidence
Finding

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Content

Scanner excerpt · SKILL.md (reported line 165)May include surrounding context.

inputHash = hex(SHA-256(salted)) // full 64 hex chars (256 bits)

text

- **Algorithm:** SHA-256, **full 64-hex-character output (256 bits)** — no truncation.
- **Salting:** the per-tenant `hashSalt` (auto-generated on first run, see Setup) is always prepended as `hashSalt + "|"` before hashing. This is mandatory; the skill never produces an unsalted hash.
- **One-way:** SHA-256 is a cryptographic hash. The server stores `inputHash` as an opaque 64-char string and uses it only to count repeats within a run. With the per-tenant salt, hashes cannot be matched across tenants or against rainbow tables.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:272