ClawHub
Back to skill

Security audit

finding-podcast-hosts-for-outreach

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Apify/Twitter workflow for finding podcast hosts, with no hidden persistence, destructive actions, or unrelated credential access found.

Install only if you are comfortable sending search terms, handles, and public Twitter/X-derived data to Apify under your APIFY_TOKEN. Keep the token protected, use conservative maxItems limits, and review any local helper script before running it.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest describes a narrow-purpose skill for finding podcast hosts and returning outreach-oriented host attributes. However, the SKILL.md inputs support arbitrary Twitter profile/tweet URLs, raw user IDs, follower/following extraction, retweeter extraction, and a custom JavaScript mapping function, which are broader generic scraping features not limited to podcast-host discovery.

Content

No source excerpt is available for this finding.

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 90)May include surrounding context.

REST API fallback:

bash
curl -X POST \
  "https://api.apify.com/v2/acts/apidojo~tweet-scraper/runs?token=$APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"searchTerms": ["entrepreneurship podcast", "new episode startup"], "maxItems": 300}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 91)May include surrounding context.

REST API fallback:

bash
curl -X POST \
  "https://api.apify.com/v2/acts/apidojo~tweet-scraper/runs?token=$APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"searchTerms": ["entrepreneurship podcast", "new episode startup"], "maxItems": 300}'

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The manifest centers the skill on using Apify Twitter scrapers to build a podcast outreach list from Twitter. The troubleshooting guidance expands the workflow to Spotify/Apple Podcasts searches, which changes the data source scope beyond the manifest's stated Twitter-based behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.