ClawHub
Back to skill

Security audit

go-perplexity

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Go API client guide for Perplexity, with credential and state-changing API risks called out rather than hidden.

Install only if you intend to use Perplexity's Go API client. Keep PERPLEXITY_API_KEY in your environment or secret manager, review upstream dependency trust, and require explicit user confirmation before invoking methods that create, update, delete, cancel, download files, or incur API costs.

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 · references/setup.md (reported line 42)May include surrounding context.

md
| `GET /v1/agent/{id}/files`, `.../files/{file_id}/content` | `ListAgentFiles`, `DownloadAgentFile` |
| `GET /v1/skills`, `/v1/skills/{skill_id}` | `ListSkills`, `GetSkill` |
| `POST /v1/skills`, `PUT /v1/skills/{skill_id}` | `CreateSkillWithBody`, `UpdateSkillWithBody` (raw body only) |
| `DELETE /v1/skills/{skill_id}` | `DeleteSkill` |
| `POST /v1/decisions` | `DecisionsV1DecisionsPost` |
| `GET /v1/analytics/computer/usage`, `/v2/...` | `GetComputerUsageAnalytics`, `GetComputerUsageAnalyticsV2` |

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The file instructs users to set an Authorization: Bearer <key> header on every request, which involves handling a credential, but it provides no caution about protecting the key from logs, source control, or accidental exposure. For markdown files, SQP-2 applies when descriptions omit warnings about behaviors that could affect privacy or security-sensitive data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.