skills/mukul975/anthropic-cybersecurity-skills/scanning-infrastructure-with-nessus/Gen Agent Trust Hub
scanning-infrastructure-with-nessus
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill parses external vulnerability scan results exported from Nessus, which represents a potential attack surface for indirect prompt injection.\n
- Ingestion points: The
NessusResultParserclass inscripts/process.pyreads and processes findings from.nessusXML files.\n - Boundary markers: No explicit instructions or delimiters are used to ensure the agent ignores any potential instructions embedded within the scan data fields.\n
- Capability inventory: The skill includes functions for performing network operations via the Nessus API and writing files to the local system.\n
- Sanitization: The skill employs the
defusedxmllibrary for parsing XML data, which effectively prevents XML External Entity (XXE) and other XML-related attacks.
Audit Metadata