spec-kitty-tasks-packages
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the
spec-kittyCLI, including a step where it executes a dynamically resolved prerequisite command. - [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it ingests untrusted data from
tasks.mdto generate new instructions. Ingestion points:feature_dir/tasks.md(Step 2). Boundary markers: Absent. Capability inventory: File write operations and shell execution viaspec-kitty. Sanitization: None; data is parsed and directly incorporated into output files. - [DATA_EXFILTRATION]: No evidence of data exfiltration was found; all operations occur within the local project environment.
- [EXTERNAL_DOWNLOADS]: The skill does not attempt to download or execute code from external or unverified network sources.
Audit Metadata