pentest-hacktricks-finder
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from community-driven external websites (HackTricks wiki and GitHub repositories). Since this content is not controlled by the skill author, it represents an ingestion surface for potentially malicious instructions hidden in technical documentation or payloads.\n
- Ingestion points: External content fetched from hacktricks.wiki and github.com via the web_fetch tool.\n
- Boundary markers: The instructions do not specify explicit delimiters or guardrails to prevent the agent from following instructions potentially embedded within the research material.\n
- Capability inventory: The skill is scoped to searching, fetching, and extracting data into a JSON structure, without direct file system or system command execution capabilities within the skill itself.\n
- Sanitization: No sanitization or validation logic is defined for the content retrieved from external sources.
Audit Metadata