ponytail-debt
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands
grepandgit blameto scan the repository files. These operations are scoped to the local environment and are used for their intended purpose of identifying and attributing code comments. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it ingests and processes untrusted data from the codebase.
- Ingestion points: Untrusted data enters the agent context via the output of
grepscanning the local repository files (SKILL.md). - Boundary markers: Absent. The instructions do not specify delimiters or provide guidance to the agent to ignore instructions embedded within the harvested 'ponytail:' comments.
- Capability inventory: The agent has the capability to execute shell commands (
grep,git blame) and perform file system writes (writing the ledger toPONYTAIL-DEBT.md). - Sanitization: Absent. There is no logic provided to sanitize or validate the content of the comments before they are formatted into the report.
Audit Metadata