setup-aeo-geo
Warn
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: MEDIUMDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: Access to sensitive configuration files.
- The skill instructs the agent to "Detect site stack" by inspecting
wp-config.php,package.json, andcomposer.json(Phase 3). Accessingwp-config.phpis high-risk because it typically contains database credentials and other sensitive environment secrets. - [COMMAND_EXECUTION]: Execution of local scripts.
- The workflow requires the execution of
scripts/calculate-share.pyandscripts/track-trend.pyto process data. While these scripts perform legitimate data aggregation, they have the capability to write files to thereports/directory. - [PROMPT_INJECTION]: Indirect prompt injection vulnerability.
- The skill processes untrusted data from user interviews and CSV files which is then included in generated reports.
- Ingestion points: User input from interviews (Phase 2) and CSV templates (
share-tracker.csv,monitoring.csv) in Phase 1 and 3. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are used when the agent processes this data.
- Capability inventory: The agent has the capability to write files to the filesystem using the provided Python scripts.
- Sanitization: There is no evidence of sanitization or escaping for data interpolated into the markdown reports, allowing an attacker to inject malicious instructions via CSV fields.
Audit Metadata