inflacion-argentina-ipc
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlto fetch JSON data fromhttps://anduin.ferminrp.comandjqto filter and process the results locally. These are standard operations for the skill's purpose. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: Data is fetched from an external API endpoint at
https://anduin.ferminrp.com/api/v1/indices/inflacion-mensual(SKILL.md). - Boundary markers: There are no explicit delimiters or instructions telling the agent to ignore potentially malicious instructions embedded within the API response.
- Capability inventory: The skill uses shell execution for data retrieval and parsing (
curl,jq). - Sanitization: The skill performs basic validation of the JSON structure (checking the
successfield and data keys) but does not sanitize the text content for prompt injection patterns.
Audit Metadata