cheerio-parsing
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): No instructions found that attempt to override agent behavior or bypass safety filters.
- Data Exposure & Exfiltration (SAFE): No hardcoded credentials or sensitive file path access detected. Network operations (axios/fetch) are consistent with the skill's primary purpose of web scraping.
- Obfuscation (SAFE): All content is provided in clear, readable markdown and JavaScript code snippets.
- Unverifiable Dependencies & Remote Code Execution (SAFE): The skill references standard, well-known Node.js packages (cheerio, axios, got). No remote script execution or piped shell commands were found.
- Privilege Escalation (SAFE): No commands for elevating system privileges or modifying sensitive system configurations.
- Persistence Mechanisms (SAFE): No attempts to establish persistence on the host system.
- Metadata Poisoning (SAFE): Metadata fields accurately describe the skill's functionality and do not contain deceptive instructions.
- Indirect Prompt Injection (LOW): The skill facilitates the ingestion of untrusted external data (web pages). While this creates an attack surface for indirect prompt injection, the skill is instructional and does not demonstrate exploitable high-privilege capabilities. Evidence: Ingestion points (axios.get in SKILL.md), Boundary markers (Absent), Capability inventory (Network read, DOM manipulation), Sanitization (Basic data extraction/normalization).
- Time-Delayed / Conditional Attacks (SAFE): No logic found that triggers behavior based on specific dates, times, or environment conditions.
- Dynamic Execution (SAFE): No usage of unsafe deserialization, eval(), or runtime code generation.
Audit Metadata