content-effort-audit
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed of markdown files containing instructional text and reference rubrics. No executable code, shell commands, or network-enabled scripts were found.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve evaluating content from user-provided URLs. This constitutes a data ingestion point for untrusted content. However, the skill does not possess any autonomous scripts or privileged capabilities (such as file writing, shell execution, or network exfiltration) that could be exploited by malicious content on those pages.
- Ingestion points: Webpage content from URLs provided by the user (SKILL.md).
- Boundary markers: Absent; the agent is instructed to scan the live URL directly for evidence.
- Capability inventory: None; the skill contains no scripts or subprocess calls.
- Sanitization: Absent.
Audit Metadata