legacy-modernizer
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze legacy codebases as part of its assessment and migration workflow. It lacks explicit instructions to differentiate between actual code logic and potentially malicious prompts that could be hidden in comments or strings within the legacy code.
- Ingestion points: User-provided legacy source code and system descriptions processed in Step 1 and Step 3.
- Boundary markers: Absent; the instructions do not provide delimiters or "ignore embedded instructions" directives for the agent when reading external code.
- Capability inventory: Coding agents utilizing this skill typically have capabilities for file system access and shell execution, which could be exploited if an injection is successful.
- Sanitization: No specific validation or sanitization steps are included to check the ingested code for adversarial prompt patterns.
Audit Metadata