ssotize
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from multiple external sources and uses it to perform mutations across various platforms.
- Ingestion points: Processes content from files, documentation, Notion, Slack, Jira, and GitHub (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the skill definition.
- Capability inventory: Mutates artifacts, modifies files, and updates documentation on external platforms.
- Sanitization: Lacks explicit sanitization of ingested content, though it includes a rule to consult a human for ambiguous contradictions.
Audit Metadata