cafci-fondos-comunes-argentina
Fail
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches financial data in JSON and XLSX formats from official Argentine domains
estadisticas.cafci.org.arandapi.pub.cafci.org.ar. It also utilizesdefuddle.mdas a proxy service to convert remote HTML content into Markdown. - [COMMAND_EXECUTION]: The instructions utilize standard system tools including
curl,jq, andpython3for data retrieval and format conversion. - [DYNAMIC_EXECUTION]: The skill uses a Python one-liner (
python3 -c) to parse HTML content. Although flagged by automated scanners due to thecurl | python3pattern, the executed code is a static script defined within the skill itself and does not execute instructions from the remote source. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions.
- Ingestion points: Markdown converted by
defuddle.mdand HTML attributes fromcafci.org.ar(Operation 5b and 6 inSKILL.md). - Boundary markers: Absent; external content is interpolated without explicit delimiters or warnings to the agent.
- Capability inventory: The agent has access to shell commands (
curl,jq,python3) and can write temporary files to/tmp(Setup section inSKILL.md). - Sanitization: Data is structured via
jqfilters and specific regex patterns in the Python parsing script, providing limited sanitization against command injection but not against natural language instruction injection.
Recommendations
- HIGH: Downloads and executes remote code from: https://estadisticas.cafci.org.ar/fondos/${FONDO_ID}?clase=${CLASE_ID} - DO NOT USE without thorough review
Audit Metadata