create-technical-spike
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates an indirect prompt injection surface by using template placeholders for user input.
- Ingestion points: Untrusted data enters the agent context via multiple
${input:...}placeholders (e.g.,SpikeTitle,Owner,Category) withinSKILL.md. - Boundary markers: Absent. The user-provided strings are directly interpolated into the YAML frontmatter and Markdown headers without delimiters or instructions to ignore embedded commands.
- Capability inventory: While the skill itself only generates a file, the 'Tools Usage' section suggests the agent has access to
runTasks,editFiles,vscodeAPI, andcodebase. If an attacker provides malicious instructions within the input fields, a downstream agent might execute them using these tools. - Sanitization: There is no evidence of sanitization, validation, or escaping of the input content before it is written to the file system.
Audit Metadata