stacktree-agent-run-report
Fail
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONCREDENTIALS_UNSAFE
Full Analysis
- [REMOTE_CODE_EXECUTION]: Automated security scanners have identified the SKILL.md file as malware and its associated domain (stacktr.ee) as a phishing site.
- [COMMAND_EXECUTION]: The skill uses
echo "$REPORT_HTML" | bash scripts/publish.shto process content. Since the HTML is built from untrusted inputs like web scrapes or logs, this creates a major command injection vulnerability. - [DATA_EXFILTRATION]: The skill sends reports, which may contain sensitive data or PII, to an external third-party domain (stacktr.ee).
- [CREDENTIALS_UNSAFE]: The skill asks for a
STACKTREE_API_KEYand points users to a URL that has been flagged for phishing. - [INDIRECT_PROMPT_INJECTION]: 1. Ingestion points: Scraped pages, tool outputs, and logs (SKILL.md). 2. Boundary markers: None present in the command pipeline. 3. Capability inventory: Subprocess bash calls and network operations. 4. Sanitization: Features a PII scanner but lacks input validation to prevent command injection in the shell pipeline.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
- AI detected serious security threats
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata