The Agent Skills Directory

[PROMPT_INJECTION] (LOW): The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from external skill files.
Ingestion points: The skill reads external SKILL.md files and directory structures at paths provided by the user, as defined in the 'Initial Analysis' step of SKILL.md.
Boundary markers: There are no explicit instructions or delimiters used to prevent the agent from following instructions that might be embedded within the files being reviewed.
Capability inventory: The skill is restricted to Read and Glob tools. It does not possess Bash, Write, or network-enabled tools, which significantly limits the potential impact of a successful injection.
Sanitization: No sanitization or filtering of external content is performed prior to the analysis and feedback generation process.

reviewing-skills