indigo-analytics
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill scripts depend on an external Javascript module located outside the skill's directory structure.
- Evidence: scripts/apr.js, scripts/dex-yields.js, scripts/governance.js, and scripts/stats.js all attempt to import core functionality from ../../../scripts/indigo-client.js. This creates an unverifiable dependency on the host environment's filesystem and external code that is not provided within the skill package.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to the ingestion of untrusted protocol data without proper sanitization or boundary markers.
- Ingestion points: Protocol data is fetched via getAprRewards, getDexYields, getProtocolParams, getPolls, getTvl, and getProtocolStats in all script files.
- Boundary markers: Absent. There are no instructions or delimiters used to separate external data from agent instructions.
- Capability inventory: The skill's primary capability is logging data to the console (scripts/apr.js, scripts/dex-yields.js, scripts/governance.js, scripts/stats.js).
- Sanitization: Absent. Data is processed via template literals or JSON stringification without filtering or escaping potentially malicious instructions embedded in the blockchain data.
Audit Metadata