security-assessment
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from a 'scope ledger' and 'planned rows' within an assessment plan to determine which sub-skills to execute. If these sources contain malicious instructions, the agent could be manipulated during the assessment workflow.
- Ingestion points: The skill reads from a 'scope ledger' and 'planned' rows in an assessment document (SKILL.md).
- Boundary markers: There are no explicit instructions to treat the data in the ledger or planned rows as untrusted or to ignore instructions embedded within them.
- Capability inventory: The skill has the capability to execute multiple sub-skills including 'web-security-assessment', 'api-security-assessment', 'android-security-assessment', 'native-binary-assessment', and 'source-security-assessment'.
- Sanitization: The instructions do not specify any validation or sanitization of the data retrieved from the ledger or rows before using it to drive the workflow.
Audit Metadata