skipfish
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEDYNAMIC_CONTEXT_INJECTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [DYNAMIC_CONTEXT_INJECTION]: The skill uses shell commands at load time to check for the presence of the
skipfishbinary and local wrapper scripts. These commands (command -vandtest -f) are benign environment checks designed to inform the agent of tool availability. - [INDIRECT_PROMPT_INJECTION]: As a web application scanner, the skill is designed to crawl and ingest data from external targets. This creates a potential surface for indirect prompt injection if the agent processes the scan results containing malicious payload strings from a compromised or adversarial target.
- Ingestion points: External URLs provided as scan targets in SKILL.md.
- Boundary markers: None explicitly defined in the provided markdown instructions.
- Capability inventory: Execution of the
skipfishbinary and local bash scripts for scanning and data processing. - Sanitization: No specific sanitization or filtering of target-derived content is mentioned.
- [COMMAND_EXECUTION]: The skill facilitates the execution of local shell scripts and system-level binaries to perform its primary function of web vulnerability scanning.
Audit Metadata