unslop
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is composed entirely of markdown instructions and does not include any executable code, scripts, or binary files.\n- [SAFE]: There are no findings related to data exfiltration, credential exposure, or unauthorized system access within the skill's instructions.\n- [INDIRECT_PROMPT_INJECTION]: The skill's purpose involves processing untrusted external text (e.g., PR bodies, Slack messages), which creates a surface for indirect prompt injection.\n
- Ingestion points: User-facing prose, including PR titles/bodies, READMEs, and messages referenced in SKILL.md.\n
- Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded commands in the source text.\n
- Capability inventory: The skill itself does not utilize any tools, perform network requests, or write to the file system.\n
- Sanitization: Absent; the instructions do not include steps to sanitize or validate the input data.
Audit Metadata