cookie-attacks
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest session cookie data from external, potentially untrusted web servers during auditing procedures, which represents an indirect prompt injection surface.
- Ingestion points: Response headers from external targets (e.g.,
https://TARGET/login) are parsed to extract session tokens. - Boundary markers: The instructions do not define explicit boundary markers or "ignore instructions" tags for the data being processed.
- Capability inventory: The skill uses
curland the Pythonrequestslibrary to replay these extracted tokens in subsequent network requests. - Sanitization: The skill uses a regular expression (
grep -oP 'SessionID=[^;]+') to extract tokens, which provides basic structural filtering, though no formal sanitization is performed on the cookie values before they are used in headers.
Audit Metadata