ads-meta
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes data from several external, untrusted sources, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: The agent is instructed to read data from
meta-data.json, Ads Manager CSV exports, and Events Manager screenshots (SKILL.md). - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external content as data only or to ignore embedded instructions.
- Capability inventory: The skill performs complex analysis and generates structured reports (
META-ADS-REPORT.md,meta-audit-results.json) based on the ingested content. - Sanitization: There is no description of sanitization, validation, or filtering processes for the external inputs.
- [COMMAND_EXECUTION]: The skill includes instructions for the user to execute a local Python script (
python3 scripts/api/meta_fetch.py) to retrieve API data. This demonstrates a dependency on local script execution for the skill's data collection phase.
Audit Metadata