secure-storage-audit
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze untrusted source code provided via the
$ARGUMENTSpath, creating a surface for indirect prompt injection. - Ingestion points: The agent reads arbitrary files (source code, configuration, documentation) from the target directory specified in
$ARGUMENTSusing theRead,Glob, andGreptools. - Boundary markers: The instructions lack explicit boundary markers or system-level warnings to the agent to ignore instructions that might be embedded in the audited files (e.g., malicious comments or README files).
- Capability inventory: The skill is granted access to powerful tools including
Bash,Task, andWebFetch. If the agent were to follow instructions embedded in the untrusted source code, it could potentially execute shell commands or perform unauthorized network requests. - Sanitization: No sanitization or filtering of the content read from the target files is specified before the agent processes it.
Audit Metadata