Back to skill

Security audit

textmock

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: scanners found no reported issues in the completed AIG scan, while Skillspector partly inspected the skill and flagged incomplete analysis of a referenced script.

The verdict is benign, but confidence is medium because Skillspector reports only 50% coverage and partial interpretation of a bundled script. Consider this unresolved evidence gap when deciding whether to install; the benign verdict does not mean risk-free.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 11)May include surrounding context.

md
node scripts/textmock-link.mjs - <<'JSON'

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

md
For an existing conversation, images, video, groups or attachments, read [Use Textmock from an agent](https://textmock.com/docs/agents). In the editor, wait for `window.textmock` or `textmock:ready`. On Mac, use the app's `textmock` command. Inspect `status`, `list` and `get` before changing a saved conversation; follow the user's chosen conversation ID. A file passed to `textmock render --out` is replaced if it exists, so use a new path or a directory when preserving files matters.

Free use allows one conversation and exports with a badge. Respect `pro_required`; only the user can subscribe. Do not import Messages, delete conversations or share private content unless the user requests that action. Use the installed API's `help` for its current fields and limits.