price-alert
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external API, creating a potential surface for indirect prompt injection.\n
- Ingestion points: The skill fetches data from api.dexscreener.com via curl and WebFetch in Step 3.\n
- Boundary markers: The WebFetch tool is prompted to return the body verbatim, but there are no explicit ignore instructions delimiters used when the agent processes the resulting JSON.\n
- Capability inventory: The skill has file system access (reads/writes to memory/), network access (curl), and the ability to send notifications via ./notify.\n
- Sanitization: The skill uses jq to extract specific fields like .priceUsd and .priceChange.h1, which limits the exposure to structured data.\n- [COMMAND_EXECUTION]: The skill uses several shell commands to manage its logic, file system operations, and state.\n
- Evidence: Usage of curl, jq, mkdir, mktemp, mv, and ./notify throughout the script.\n- [EXTERNAL_DOWNLOADS]: Fetches real-time price data from a well-known cryptocurrency data service.\n
- Evidence: Network requests to api.dexscreener.com in Step 3.
Audit Metadata