revops
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is instructed to ingest and prioritize information from local configuration files, creating a potential surface for indirect prompt injection if those files are modified by an attacker.\n
- Ingestion points: The skill reads from .agents/product-marketing-context.md (or .claude/product-marketing-context.md) to gather product context.\n
- Boundary markers: There are no explicit instructions or delimiters used to prevent the agent from being influenced by malicious instructions embedded within the ingested context file.\n
- Capability inventory: The skill is primarily instructional and does not include any tools or scripts for network operations, file system modification, or command-line execution.\n
- Sanitization: No data validation or sanitization is performed on the content read from the context files.\n- [NO_CODE]: The skill and its associated reference files contain only informational markdown text and templates. No executable code, such as Python or Shell scripts, is provided or executed.
Audit Metadata