trailsnap-cli
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content from external API responses, such as photo descriptions and narratives, which could serve as an attack surface for indirect prompt injection.
- Ingestion points:
reference.mddocumentation for thephotos infocommand shows it returnsdescriptionandnarrativefields. - Boundary markers: None mentioned in the instructions for handling these text fields.
- Capability inventory: The skill has the ability to list, read, and delete photos via the
trailsnapCLI. - Sanitization: No explicit instructions for sanitizing or escaping these fields before they are processed by the agent.
- [COMMAND_EXECUTION]: The skill requires the execution of a local CLI binary (
trailsnap) to perform its functions. - Evidence:
SKILL.mdandreference.mddetail numerous shell commands for managing photos, albums, and locations. - Context: All commands are consistent with the skill's stated purpose and are scoped to the
trailsnaptoolset. - [SAFE]: External dependencies and installation steps point to the vendor's own official packages and repositories.
- Evidence:
install.mdreferencesnpm install -g trailsnap-cliandnpx skills add lc044/trailsnap, which align with the author's identity.
Audit Metadata