Back to skill

Security audit

screener-docs

Security checks for vulnerabilities and agentic risk

Overview

This skill downloads Screener.in-linked company documents into a local folder, and its network and file-writing behavior is disclosed and aligned with that purpose.

Install only if you are comfortable with the skill downloading files from Screener.in-linked third-party sites and saving them under the chosen output folder. Prefer a dedicated output directory, use dry-run or list-matches for ambiguous companies, and avoid exporting SCREENER_SESSIONID unless Screener.in actually requires login. Pinning dependencies would improve reproducibility.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill invokes Python, reads optional environment state (SCREENER_SESSIONID), accesses local paths, and downloads files from external sites, yet it declares no explicit tool or permission scope. That creates a governance gap: an agent may auto-run a network-and-filesystem-capable skill without clear sandboxing or user-consent boundaries, increasing the chance of unintended downloads or writes.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation rule is broad enough to trigger on many ordinary requests that mention a company and verbs like fetch, pull, or collect, even when the user may not intend bulk document downloads. In an agent setting, overbroad triggering can cause unnecessary network activity, local file writes, and possible use of authenticated session context without sufficiently specific user intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

Although the skill mentions output layout, it does not prominently warn that running it will create multiple files and a manifest under a local directory, potentially across several subfolders. In an automated agent workflow, weak disclosure around local writes can surprise users, clutter disks, or place downloaded content in unintended locations.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
96% confidence
Finding

The dependency 'requests' is unpinned, so builds may resolve to different versions over time, including versions with security defects or breaking changes. In a skill that downloads remote documents from the internet, dependency drift increases supply-chain risk and can expose the downloader to known library flaws unexpectedly.

Content

Scanner excerpt · requirements.txt (reported line 1)May include surrounding context.

text
requests
beautifulsoup4

Unverifiable Dependency: requests has 16 known advisory(ies) (CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +13 more), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
91% confidence
Finding

The manifest includes 'requests' without a version pin, and the package has multiple historical advisories; without pinning, it is impossible to verify whether deployment will select a patched or vulnerable release. This is more concerning here because the skill fetches content from external sites, so any client-side flaw in HTTP handling, redirects, TLS, auth, or URL parsing could be reachable during normal operation.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
90% confidence
Finding

The dependency 'beautifulsoup4' is also unpinned, which makes installations non-reproducible and allows future dependency resolution to silently introduce vulnerable or incompatible releases. Although this package is typically lower risk than a networking library, it still expands the supply-chain attack surface.

Content

Scanner excerpt · requirements.txt (reported line 2)May include surrounding context.

text
requests
beautifulsoup4