woo-sailor
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external files (e.g.,
SKILL.md,CLAUDE.md,AGENT.md) which represents a potential attack surface for indirect prompt injection. - Ingestion points: Files matching glob patterns
**/SKILL.md,**/CLAUDE.md,**/AGENT.md,**/agents/*.md, and**/rules/*.mdare read into the agent's context inSKILL.md(e.g., "Read it to understand why the user wanted optimizations applied"). - Boundary markers: The instructions do not define specific boundary markers or explicit warnings to the sub-agent to ignore instructions embedded within the target files.
- Capability inventory: The skill spawns a sub-agent (
process-siren:process-siren) with the capability to perform in-place file modifications ("Optimize all processes in this file in-place"). - Sanitization: There is no evidence of sanitization or filtering of the target file content before it is processed by the sub-agent.
Audit Metadata