ClawHub
Back to skill

Security audit

Gist Page Preview

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: helps publish user-requested demos to GitHub Gists and generate gists.page preview links.

Install only if you want agents to publish files to GitHub Gists. Before using it, confirm which files will be uploaded, whether the gist is secret or public, and that the content contains no secrets, tokens, private data, or internal material. Prefer a narrowly scoped GitHub token for gist publishing.

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

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly instructs the agent to check $GH_TOKEN / $GITHUB_TOKEN before asking the user for a token, which can lead an agent to access ambient credentials without first obtaining user consent or warning the user. In an agent setting, environment tokens are sensitive secrets and using them to publish content externally can violate least-privilege and user expectations even if the destination is legitimate GitHub infrastructure.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

This instruction sends local file contents to an external service (GitHub Gists) using curl with bearer-token authentication. External publication is the core purpose of the skill, but without a mandatory confirmation step and data-sensitivity warning, an agent could upload proprietary, private, or regulated content to a public or unlisted remote location.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

bash
jq -n --rawfile h index.html '{public: false, files: {"index.html": {content: $h}}}' |
curl -sS -X POST https://api.github.com/gists \
  -H "Authorization: Bearer $GITHUB_TOKEN" \
  -H "Accept: application/vnd.github+json" \
  -d @- | jq -r '.id'

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

This instruction sends local file contents to an external service (GitHub Gists) using curl with bearer-token authentication. External publication is the core purpose of the skill, but without a mandatory confirmation step and data-sensitivity warning, an agent could upload proprietary, private, or regulated content to a public or unlisted remote location.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

bash
jq -n --rawfile h index.html '{public: false, files: {"index.html": {content: $h}}}' |
curl -sS -X POST https://api.github.com/gists \
  -H "Authorization: Bearer $GITHUB_TOKEN" \
  -H "Accept: application/vnd.github+json" \
  -d @- | jq -r '.id'

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 76)May include surrounding context.

md
- gh: `gh gist edit <id> --add <file>` uploads that file (adds or replaces). Bare
  `gh gist edit <id>` opens an interactive `$EDITOR` — avoid in agent sessions.
- MCP: `update_gist` (or equivalent), one file per call.
- API: `PATCH https://api.github.com/gists/<id>` with the same `files` body shape as
  creation; set a file's value to `null` to delete it.
- git: clone `https://gist.github.com/<id>.git`, commit, push (HTTPS auth: any
  username, token as password).

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 83)May include surrounding context.

md
- gh: `gh gist edit <id> --add <file>` uploads that file (adds or replaces). Bare
  `gh gist edit <id>` opens an interactive `$EDITOR` — avoid in agent sessions.
- MCP: `update_gist` (or equivalent), one file per call.
- API: `PATCH https://api.github.com/gists/<id>` with the same `files` body shape as
  creation; set a file's value to `null` to delete it.
- git: clone `https://gist.github.com/<id>.git`, commit, push (HTTPS auth: any
  username, token as password).

Static analysis

No suspicious patterns detected.