repurpose
Fail
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: HIGHDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill instructions direct the agent to read content from a user-provided file path. This provides a mechanism for an attacker to expose sensitive local files, such as configuration files, environment variables (.env), or private keys, by providing their paths as input to the repurpose command.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from external sources and uses it to drive automated workflows.
- Ingestion points: Untrusted data enters the context via external URLs (WebFetch) and local file reads.
- Boundary markers: There are no markers or delimiters used to separate fetched content from the skill's instructions.
- Capability inventory: The skill has the capability to generate content and interact with external social media scheduling tools for automated publishing.
- Sanitization: The instructions lack any requirement to validate, sanitize, or filter the external content for malicious instructions before processing.
Recommendations
- AI detected serious security threats
Audit Metadata