Back to skill

Security audit

gifgrep

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to do what it says: search, download, and process GIFs using external GIF services and a local CLI.

Install only if you are comfortable with a third-party GIF CLI, queries being sent to Tenor or Giphy, and generated/downloaded files being written to chosen output paths. Prefer a pinned, reviewed gifgrep version when available and provide only the API keys needed for the provider you use.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:19
Finding

Unpinned Go CLI Dependency Allows Supply-Chain Compromise

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 19-22
Vulnerability Type: T08: Insecure Dependencies
Risk Level: Medium

Vulnerable Code

json
{
  "type": "go",
  "package": "github.com/steipete/gifgrep/cmd/gifgrep@latest",
  "label": "Install GifGrep CLI (Go)"
}

Technical Analysis

The installation metadata specifies the mutable Go version selector @latest. Consequently, the executable installed in the future may differ from the version available when this Skill was reviewed. The dependency's implementation is not included in the project, so its behavior cannot be verified by auditing SKILL.md.

If the upstream repository, release process, or maintainer account is compromised, a malicious release could become the version resolved by @latest. Installing that version would compile or retrieve attacker-controlled dependency code and create a locally executable gifgrep binary. No checksum, immutable commit, or fixed semantic version is specified to ensure that the installed artifact matches an audited release.

Attack Path

  1. An attacker compromises the upstream github.com/steipete/gifgrep repository, its maintainer credentials, or its release process.
  2. The attacker publishes malicious code in the revision selected by Go's @latest resolution.
  3. A user or agent installs the CLI using the installation metadata in SKILL.md.
  4. Go resolves and installs the attacker-controlled revision without validating it against a project-defined version or checksum.
  5. When the installed gifgrep executable is invoked, the malicious payload runs with the privileges and environment of the invoking user.
  6. The payload may access files available to that user and environment variables inherited by the process, potentially including GIPHY_API_KEY and TENOR_API_KEY.

Impact Assessment

Successful exploitation could allow arbitrary code execution under the account that inst ...[truncated 525 chars]

Remediation
View remediation

Remediation Suggestions

  1. Replace @latest with a specific, reviewed release version, for example:
    json
    {
      "type": "go",
      "package": "github.com/steipete/gifgrep/cmd/gifgrep@v1.0.0",
      "label": "Install GifGrep CLI (Go)"
    }
    
  2. Verify the selected release against an immutable commit and document the expected source commit or artifact checksum.
  3. Where supported, require checksum or signature verification before installing precompiled artifacts.
  4. Review dependency updates explicitly rather than allowing installation metadata to resolve new versions automatically.
  5. Apply equivalent version pinning and integrity verification to the custom Homebrew tap installation option.
  6. Run the CLI with least privilege and expose only the API credentials and filesystem paths necessary for the requested operation.
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 (1)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly supports external GIF search against Tenor/Giphy and can download results to arbitrary local output paths, but it does not clearly warn users that invoking these tools will make network requests and write files. This is a real safety/transparency issue because agents may trigger data egress or filesystem modifications without the user fully realizing those side effects, even though the behavior appears consistent with the skill’s stated purpose.

Content

No source excerpt is available for this finding.