institutional-13f-tracker

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is strictly read-only, utilizing GET requests to the official vendor domain app.sentisense.ai to retrieve public financial filings.
  • [SAFE]: Authentication is managed through a required environment variable (SENTISENSE_API_KEY), following secret management best practices for API keys.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external API responses, creating a potential surface for indirect instructions, although no exploitable capabilities are present in the skill.
  • Ingestion points: Data is ingested from the https://app.sentisense.ai endpoints as described in SKILL.md.
  • Boundary markers: No explicit boundary markers or delimiters for the API content are defined in the instructions to the agent.
  • Capability inventory: The skill contains no scripts or tools with file-writing, command execution, or network-writing capabilities; its scope is limited to providing informational context.
  • Sanitization: No specific sanitization or filtering of the API data is mentioned in the instruction set.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 04:26 AM
Security Audit — agent-trust-hub — institutional-13f-tracker