revops-kickoff
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates as a logical router and project state manager. It does not perform network operations, exfiltrate credentials, or execute arbitrary code.- [INDIRECT_PROMPT_INJECTION]: The skill reads project files such as the README, data dictionaries, and git logs to automate the identification of project context. While this ingestion of untrusted repository content represents a potential indirect prompt injection surface, it is considered safe in this context due to the skill's lack of high-risk capabilities like network access or shell execution.
- Ingestion points: README, data dictionaries, stage documentation, .github/ folder, and git logs as described in SKILL.md.
- Boundary markers: None explicitly defined for external content.
- Capability inventory: The skill's primary actions are reading project metadata and writing session logs/state to local files ('revops-context.md' and the 'memories/' directory).
- Sanitization: The skill includes explicit instructions to exclude PII, customer names, and sensitive financial data from its memory storage (SKILL.md § 6).
Audit Metadata