ponytail-debt
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository by scanning for
ponytail:comments. - Ingestion points: SKILL.md specifies scanning the repository using
grepto find and process comment markers. - Boundary markers: No specific delimiters or instructions to ignore embedded commands within the processed comments are defined.
- Capability inventory: The skill uses
grepandgit blamefor data collection and has the ability to write reports to the file system (e.g.,PONYTAIL-DEBT.md). - Sanitization: The instructions do not include steps to sanitize or escape the content of the comments before they are processed or written to a file.
Audit Metadata