career-gap-planner
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted external data from job descriptions and resumes (Category 8).
- Ingestion points: Untrusted text from job descriptions and user-supplied experience data is ingested during the intake phase in SKILL.md (Step 1).
- Boundary markers: The agentic protocol lacks explicit delimiters or instructions to treat external input as untrusted data to prevent the execution of embedded commands.
- Capability inventory: The skill has access to the WebSearch tool to find learning resources based on the identified gaps, as described in SKILL.md (Step 4) and references/resource-finding.md.
- Sanitization: There are no defined procedures for sanitizing or escaping the content of ingested job descriptions or resume text before processing.
Audit Metadata