vike-hl-position-match
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data (position details from share cards) and interpolates it into command-line arguments, which creates a potential surface for injection attacks.
- Ingestion points: User-provided data for asset symbols, leverage, and entry prices as described in the instructions and common queries in SKILL.md.
- Boundary markers: Absent. The skill does not instruct the agent to use delimiters or specify that the input should be treated as literal, non-executable text.
- Capability inventory: The skill executes the
vike-dataCLI tool via a Bash shell environment. - Sanitization: There are no instructions provided to validate, escape, or sanitize the user-supplied position details before they are passed as flags to the tool.
Audit Metadata