stock-metrics
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it interpolates untrusted website data from the
{extract_results}placeholder directly into the agent context without boundary markers or instructions to disregard embedded commands. - Ingestion points: Untrusted content is ingested via the
{extract_results}variable inSKILL.md. - Boundary markers: Absent. The skill does not use delimiters (e.g., XML tags or triple backticks) to isolate external data from its own instructions.
- Capability inventory: No dangerous capabilities such as file system writes or shell execution were detected in this skill.
- Sanitization: No sanitization or filtering logic is present to handle potentially malicious instructions within the source data.
Audit Metadata