apex-decompose
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs legitimate code analysis tasks using local scripts. No evidence of malicious intent, data exfiltration, or obfuscation was found during the audit.\n- [INDIRECT_PROMPT_INJECTION]: The skill reads source code from a user-specified directory, which is a potential surface for indirect prompt injection attacks where malicious content in source code could influence the agent.\n
- Ingestion points: Source code files and dependency manifests are read from the user-provided directory in
SKILL.mdand by the analysis scripts in thescripts/directory.\n - Boundary markers: The instructions do not define specific delimiters or warnings for the agent to ignore instructions embedded within the ingested source code.\n
- Capability inventory: The skill has capabilities to read local files and write specification documents to the
specs/directory.\n - Sanitization: No sanitization or content filtering is applied to the source code before it is processed by the agent.
Audit Metadata