linkfox-sif-keyword-overview

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script scripts/sif_keyword_overview.py to process user queries and interact with the LinkFox API. This script is well-structured and performs input validation on the keyword and country parameters.
  • [EXTERNAL_DOWNLOADS]: The skill performs network requests to https://tool-gateway.linkfox.com/sif/keywordOverview to fetch market data and https://skill-api.linkfox.com/api/v1/public/feedback to report usage feedback. These endpoints are owned by the skill's vendor and represent the primary intended functionality of the skill.
  • [DATA_EXPOSURE]: The skill utilizes an environment variable LINKFOXAGENT_API_KEY for API authentication. This is a standard and recommended practice for managing secrets in AI agent environments, and there is no evidence of this key being transmitted to unauthorized third parties.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing user-supplied keywords and rendering data from an external API.
  • Ingestion points: The keyword parameter is accepted via user input and passed to the API call in scripts/sif_keyword_overview.py.
  • Boundary markers: There are no explicit boundary markers or instructions in SKILL.md directing the agent to ignore potential instructions embedded within the keywords or the resulting API response.
  • Capability inventory: The skill includes network access via Python's urllib library in scripts/sif_keyword_overview.py.
  • Sanitization: The script implements basic length validation (1000 characters) and standard JSON serialization for the API payload, which mitigates simple injection attempts.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 11:55 AM