developmental-progression-synthesis
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted external data (
kud_charts) provided by the user. - Ingestion points: External data enters the agent context via the
{{kud_charts}}and{{competency_structure}}variables inSKILL.md. - Boundary markers: The prompt uses section headers for organization but lacks explicit delimiters or instructions to ignore potential commands embedded within the provided curriculum data.
- Capability inventory: The skill has no active capabilities; it has no code, no tools, and
disable-model-invocation: trueis set in the frontmatter, meaning it cannot execute commands or make network requests regardless of input content. - Sanitization: There is no evidence of input validation or sanitization for the curriculum data inputs.
- [NO_CODE]: The skill consists entirely of Markdown instructions and theoretical frameworks. It does not include any scripts, executable binaries, or external library dependencies, significantly reducing the attack surface.
Audit Metadata