moltbook-posting
Fail
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: HIGHDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill accesses the sensitive file path
~/.alex/config.yamlto read API keys and base URL configurations. - [DATA_EXFILTRATION]: Credential exposure risk exists because the skill sends the retrieved API key in the Authorization header to any URL specified in the
MOLTBOOK_API_FALLBACK_URLSenvironment variable. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting untrusted data from the Moltbook API and Bing RSS fallback results.
- Ingestion points: Untrusted external data is fetched in
run.pyvia thefeedandsearchactions. - Boundary markers: No boundary markers or protective instructions are implemented to prevent the agent from executing commands embedded in the retrieved content.
- Capability inventory: The skill has the capability to perform network POST requests and read local configuration files.
- Sanitization: No sanitization, filtering, or validation is performed on the data fetched from external sources before it is returned to the agent context.
Recommendations
- AI detected serious security threats
Audit Metadata