ops-oncall-log
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external monitoring systems (alert titles and event details) and wiki pages (templates and existing logs) to generate summaries. Because these sources are potentially attacker-controlled (e.g., an attacker triggering an alert with a malicious name) and the skill lacks explicit instructions to sanitize or delimit this input, it is vulnerable to indirect prompt injection.
- Ingestion points: Monitoring alert events (SKILL.md Step 4b), Wiki template pages (SKILL.md Step 6), and existing Wiki log pages (SKILL.md Step 4a).
- Boundary markers: Absent. The instructions do not define delimiters or warnings for the agent to ignore embedded instructions within the fetched data.
- Capability inventory: The skill is authorized to use
Read,Glob,Grep, andBashtools, along with Monitoring and Wiki-specific MCP tools. - Sanitization: Absent. No escaping or validation of external content is performed before the data is processed into the final wiki page structure.
Audit Metadata