Back to skill

Security audit

Human in the Loop — Approval Gates for Agent Writes

Security checks for vulnerabilities and agentic risk

Overview

This skill is benign: it implements a disclosed local approval ledger and lock helper for human-reviewed actions, without hidden network calls or automatic execution.

Install only if you want a local approval state file for workflows that may create records, drafts, payments, or similar changes. Choose state and lock paths deliberately, protect the approval secret, and prune old applied items only after your reconciliation lookups no longer need them.

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
Vulnerability Patterns
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill explicitly describes file read/write behavior via a local JSON state file, lock sidecar, and per-application lock files, but it does not declare any tool scope such as permissions or allowed-tools. That mismatch can let an agent invoke filesystem-capable tools without an explicit contract, weakening least-privilege controls and making unintended local state modification more likely.

Content

No source excerpt is available for this finding.

Unbounded Output

Medium
Category
Output Handling
Confidence
80% 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 30)May include surrounding context.

md
| "the job timed out, did it create the record?" | §4: reconcile, never re-run the creation |
| "two runs of the cron hit the same app" | §5: run lock |
| "the agent only prepares drafts, a human sends them" | §6: `regime="draft_only"`, filter in code |
| Auditing an existing approval flow | Fill the Output Format, one row per rule |

## States and named gates

Static analysis

No suspicious patterns detected.