tester
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple external and internal sources to drive its testing logic and report generation. This ingestion creates a surface where malicious instructions embedded in documentation or project tickets could potentially influence the agent's behavior.
- Ingestion points: The skill retrieves library documentation using
mcp__context7__query-docs(SKILL.md), performs web research viaWebSearch/WebFetch(SKILL.md), and reads behavioral acceptance criteria directly from project tickets (SKILL.md,tester.md). - Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands (e.g., XML tags or specific delimiters) when the agent processes the retrieved external content.
- Capability inventory: The skill is capable of writing state and reports to the local file system (
testing/qa-{ticket}.md), creating documentation in Confluence (createConfluencePage), and modifying project tickets in Jira (createJiraIssue,addCommentToJiraIssue). - Sanitization: The skill lacks explicit instructions for sanitizing or validating external content before it is interpolated into prompts or recorded in persistent storage.
Audit Metadata