work-tracking
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The instructions direct the agent to triage incoming requests and read existing project records. Processing data from these external, potentially untrusted sources creates an attack surface for indirect prompt injection.
- Ingestion points: External work records and intake channels described in SKILL.md.
- Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded in the external records.
- Capability inventory: The skill does not include any scripts or code, relying on the agent's base capabilities for execution.
- Sanitization: No specific steps for sanitizing or validating external record content are provided.
- [NO_CODE]: The skill consists entirely of markdown-based instructions and process descriptions without any executable scripts or command-line configuration.
Audit Metadata