social-content
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, hidden commands, or suspicious instructions were found. The skill serves its stated purpose of social media strategy support.\n- [NO_CODE]: The skill consists entirely of instructional markdown and evaluation data. It contains no scripts or binaries, which significantly minimizes the attack surface.\n- [PROMPT_INJECTION]: The skill establishes a surface for indirect prompt injection through external data ingestion, but lacks executable capabilities for exploitation.\n
- Ingestion points: Instructions to read '.agents/product-marketing-context.md' or '.claude/product-marketing-context.md' in SKILL.md.\n
- Boundary markers: Absent; no specific delimiters are defined to isolate the context file's content.\n
- Capability inventory: None; the skill does not include any scripts or tools capable of performing file writes, network requests, or command execution.\n
- Sanitization: Absent; no filtering or validation logic is applied to the ingested content.
Audit Metadata