ClawHub
Back to skill

Security audit

patron-ig-f100k

Security checks for vulnerabilities and agentic risk

Overview

The skill’s Instagram analytics purpose is coherent, but it automatically sources a local secrets file and sends reel URLs to a third-party transcription service, so it deserves review before installation.

Review this skill before installing. It is not clearly malicious, but it should only be used if you are comfortable sharing Instagram reel URLs with Supadata, using Apify for Instagram scraping, and letting the agent update a persistent patterns memory file. Prefer providing only SUPADATA_API_KEY through a scoped secret mechanism instead of allowing the skill to source a whole secrets.env file.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Credential Access

High
Category
Privilege Escalation
Confidence
88% confidence
Finding

The skill instructs sourcing a local secrets file into the shell environment at runtime, which is a form of credential access beyond using already-provisioned environment variables. In an agent setting, this broadens secret exposure and can unintentionally grant the skill access to additional credentials present in the file, especially if the file contains more than the single API key needed.

Content

Scanner excerpt · SKILL.md (reported line 87)May include surrounding context.

Para CADA video/reel filtrado, ejecutar:

bash
[ -z "$SUPADATA_API_KEY" ] && [ -f "$HOME/.config/f100k/secrets.env" ] && set -a && . "$HOME/.config/f100k/secrets.env" && set +a
curl -s -X GET "https://api.supadata.ai/v1/transcript?url=https://www.instagram.com/reel/[shortCode]/" \
  -H "x-api-key: $SUPADATA_API_KEY"

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill sends Instagram reel URLs to a third-party transcription service without an explicit disclosure or consent step tied to that transmission. Even if the reels are public, this shares user-associated content and behavioral metadata with an external processor, creating privacy, compliance, and unexpected data-handling risks.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

This is a real external transmission: the skill performs an HTTP request to Supadata containing a reel URL, which discloses user-related content to a third party. In this skill's context, the transmission is functionally necessary for transcription, but it still expands the trust boundary and introduces privacy and data governance risk.

Content

Scanner excerpt · SKILL.md (reported line 88)May include surrounding context.

bash
[ -z "$SUPADATA_API_KEY" ] && [ -f "$HOME/.config/f100k/secrets.env" ] && set -a && . "$HOME/.config/f100k/secrets.env" && set +a
curl -s -X GET "https://api.supadata.ai/v1/transcript?url=https://www.instagram.com/reel/[shortCode]/" \
  -H "x-api-key: $SUPADATA_API_KEY"

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill instructs the agent to automatically write persistent memory files and update an index without requiring explicit user confirmation at execution time. In an agent context, silent file modification can surprise users, pollute long-term memory, and create integrity issues if the analysis is wrong or triggered unexpectedly by automation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

Hardcoding 'lunes que viene a las 08:05 Lima' in the final output can misrepresent when automation will actually run if the user's timezone differs. While low severity, this can cause operational confusion, missed reviews, or actions occurring at unintended times in an automated workflow.

Content

No source excerpt is available for this finding.