ClawHub
Back to skill

Security audit

HookPulse

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward HookPulse monitoring integration whose external API calls and monitor-management powers match its stated purpose.

Install only if you are comfortable using hookpulse.net as the monitoring backend. Treat guest tokens, setup keys, and monitor IDs as credentials, avoid posting them in public logs, and review billing before creating many monitors or adding alert destinations.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 34)May include surrounding context.

md
| `list_endpoints` | `GET /api/endpoints` | List the monitors and their state. |
| `get_endpoint` | `GET /api/endpoints/{id}` | Read one monitor: state, next expected time, last check-in. |
| `list_events` | `GET /api/endpoints/{id}/events` | Read the latest check-ins of a monitor. |
| `delete_endpoint` | `DELETE /api/endpoints/{id}` | Remove a monitor. |
| `ping_ingest` | `GET /in/{id}` | Send a success check-in, as the routine does. |
| `signal_start` | `GET /in/{id}/start` | Record that a run started, to measure its duration. |
| `signal_fail` | `GET /in/{id}/fail` | Record a failed run; the alert leaves on the next five-minute check. |

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

bash
# Guest token, then a monitor for a backup at 03:00 São Paulo time with 15 minutes of allowed delay
HP=$(curl -s -XPOST https://hookpulse.net/api/guest | jq -r .token)
curl -s -XPOST https://hookpulse.net/api/endpoints -H "X-Guest-Token: $HP" -H 'content-type: application/json' \
  -d '{"name":"nightly-backup","cron":"0 3 * * *","tz":"America/Sao_Paulo","grace_sec":900}'

# At the end of the routine: the exit code of the last command

Static analysis

No suspicious patterns detected.