task-planning
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The script
tests/run-validation.pyusesexec()andcompile()to load and execute the contents of the internal utility scriptscripts/validate-output.py. - Evidence:
exec(compile(validator_source, str(SKILL_DIR / "scripts" / "validate-output.py"), "exec"), validator_namespace)intests/run-validation.py. - Context: This pattern is used as a lightweight mechanism to import and execute testing logic from a sibling file within the skill's own package without formal module installation. It targets a static local file path.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user input in the form of project specifications and requirements, which defines an attack surface for indirect prompt injection.
- Ingestion points: User-provided project specifications, features, or migration briefs described in
SKILL.md. - Boundary markers: Absent; the instructions do not specify the use of delimiters or specific warnings to ignore embedded instructions within user-provided specifications.
- Capability inventory: Execution of internal Python scripts
scripts/validate-output.pyandtests/run-validation.pyvia shell commands; file reading of bundled assets and rules. - Sanitization: Absent; user input is processed as raw text without explicit sanitization or validation of its content prior to processing by the model.
Audit Metadata