account-recovery-plan
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided descriptions about locked or hacked accounts, which serves as an ingestion point for external data. This creates a surface for indirect prompt injection, though the risk is negligible since the skill has no access to sensitive tools, file systems, or network capabilities.
- Ingestion points: User descriptions of accounts, symptoms of compromise, and linked accounts as defined in the 'Required Inputs' section of SKILL.md.
- Boundary markers: No explicit delimiters or warnings are used to isolate user data from instructions.
- Capability inventory: None; the skill defines no executable scripts or platform tools.
- Sanitization: None identified; input is handled as natural language text.
- [NO_CODE]: The skill is a purely informational markdown file. It contains no code, binaries, or automated workflows, posing no direct threat to the execution environment.
Audit Metadata