trade
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted market data from the web.\n
- Ingestion points: The skill uses
web_searchandweb_extractto fetch news, sentiment, analyst ratings, and transcripts (SKILL.md).\n - Boundary markers: No protective delimiters or instructions to ignore embedded commands are present in the orchestrator instructions.\n
- Capability inventory: The agent has access to
terminal,execute_code, and task delegation tools, which could be exploited if malicious instructions are processed.\n - Sanitization: No evidence of data sanitization or validation of the scraped content is specified.\n- [COMMAND_EXECUTION]: The skill executes a local Python script (
generate_trade_pdf.py) located in the skill's installation directory (~/.hermes/skills/trade/scripts/). This execution is part of the skill's intended functionality for report generation.
Audit Metadata