cometchat-angular-troubleshooting

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill establishes a surface for indirect prompt injection by instructing the agent to ingest and analyze untrusted data from the user's local project environment.
  • Ingestion points: The skill reads contents from files such as angular.json, src/app/app.component.ts, src/app/app.module.ts, and searches across all HTML templates using executeBash (grep) and readFile.
  • Boundary markers: The instructions do not specify any delimiters or instructions for the agent to ignore potential malicious prompts embedded within the source code or configuration data it processes.
  • Capability inventory: The agent is granted capabilities including executeBash, readFile, and fileSearch, which could be exploited if the agent follows instructions found within the project files.
  • Sanitization: No sanitization or validation logic is defined for the data retrieved from the local file system before it enters the agent's context.
  • [SAFE]: All external resources and package dependencies (e.g., @cometchat/chat-uikit-angular) are official vendor assets belonging to CometChat, with no evidence of typosquatting or malicious sourcing.
  • [SAFE]: The skill includes security-conscious advice, such as recommending the use of server-minted auth tokens instead of hardcoding Auth Keys in client-side production environments.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 07:49 AM
Security Audit — agent-trust-hub — cometchat-angular-troubleshooting