prompt-literacy-sequence-designer
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill's instructions and metadata do not contain any malicious patterns, such as obfuscation, credential exfiltration, or persistence mechanisms.
- [NO_CODE]: There are no executable scripts, shell commands, or dependencies included in this skill, eliminating traditional code execution risks.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted user data via several placeholders. 1. Ingestion points: Untrusted data enters through fields like 'common_student_prompts' and 'subject_area' in SKILL.md. 2. Boundary markers: The prompt does not use specific delimiters or 'ignore' instructions to isolate these inputs. 3. Capability inventory: The agent has no access to tools, subprocesses, or network operations while using this skill. 4. Sanitization: No sanitization or escaping of input variables is implemented. Given the absence of exploitable capabilities, this finding is considered low risk and does not impact the safety of the skill.
Audit Metadata